Article(id=1322961075985056718, tenantId=1146029695717560320, journalId=1249024232475115590, issueId=1322960856543273127, articleNumber=null, orderNo=null, doi=10.11834/jig.250519, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1762272000000, receivedDateStr=2025-11-05, revisedDate=1766073600000, revisedDateStr=2025-12-19, acceptedDate=null, acceptedDateStr=null, onlineDate=1793348099942, onlineDateStr=2026-10-30, pubDate=1786809600000, pubDateStr=2026-08-16, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793348099942, onlineIssueDateStr=2026-10-30, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793348099942, creator=13701087609, updateTime=1793348099942, updator=13701087609, issue=Issue{id=1322960856543273127, tenantId=1146029695717560320, journalId=1249024232475115590, year='2026', volume='31', issue='8', pageStart='2687', pageEnd='3074', issueExtLink='null', onlineDate='null', pubDate='1786809600000', pubDateStr='2026-08-16', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1793348047624, creator='13701087609', updateTime=1793348605344, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1322963195874378645, tenantId=1146029695717560320, journalId=1249024232475115590, issueId=1322960856543273127, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1322963195874378646, tenantId=1146029695717560320, journalId=1249024232475115590, issueId=1322960856543273127, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=2897, endPage=2910, ext={EN=ArticleExt(id=1322961078086403023, articleId=1322961075985056718, tenantId=1146029695717560320, journalId=1249024232475115590, language=EN, title=Lightweight image super-resolution network with sparse and permuted self-attention, columnId=1322960981189603998, journalTitle=Journal of Image and Graphics, columnName=Image Processing and Coding, runingTitle=null, highlight=null, articleAbstract=
Objective Image super-resolution （SR） is a fundamental low-level vision task in computer vision that aims to reconstruct high-resolution images from low-resolution inputs，thereby enhancing image detail quality and sharpness. High-quality reconstruction not only improves human visual perception but also provides clear and highly structured input features for high-level vision tasks，such as object detection，semantic segmentation，and face recognition. Therefore，SR technology has broad application prospects in intelligent surveillance，medical imaging，autonomous driving，satellite remote sensing，and related fields. Convolutional neural networks （CNNs） have been widely used for SR because of their ability to capture local textures and edges. However，their limited receptive fields hinder the modeling of long-range dependencies，which are essential for preserving global structural consistency. Transformer-based methods，by contrast，leverage self-attention mechanisms to capture the global context，achieving superior reconstruction performance. Despite this advantage，conventional Transformers suffer from high computational costs and redundant attention weight，limiting their applicability in lightweight or real-time scenarios. To address these challenges，we propose a lightweight SR network that integrates the advantages of CNN and Transformer architectures. The network integrates efficient local feature extraction with global context modeling，achieving balance between reconstruction quality and computational efficiency.
Method We propose SPSANet，a lightweight image SR network that is based on sparse and permuted self-attention （SPSA） and composed of shallow feature extraction，deep feature extraction，and high-resolution reconstruction. At the shallow feature extraction stage，a standard 3 × 3 convolution captures basic texture information，and shallow features are forwarded to the reconstruction stage via a long skip connection to provide residual guidance. The deep feature extraction stage consists of four SPSA groups，each containing six SPSA blocks and a convolutional layer. Each block integrates an SPSA module （SPSAM） that expands the receptive field while reducing attention redundancy，a high-frequency enhancement module （HFEM） for refining texture and edge details，and a dual-branch feature fusion module （DBFFM） that effectively fuses global and local features through spatial–channel interactions. Then，shallow and deep features are fused via a global residual connection，and a pixel shuffle operation generates the final high-resolution output. Our method is implemented on the PyTorch framework and trained using an NVIDIA RTX 3090 GPU. The training dataset is DIV2K，which contains 800 images. For the ×2 SR task，the model is trained for a total of 500 K iterations by using the Adam optimizer with an initial learning rate of 2 × 10⁻⁴. The input image patch size is fixed at 64 × 64，the batch size is set to 16，and the MultiStepLR scheduler is applied to halve the learning rate at iterations ［250 K，400 K，450 K，475 K］. For the ×3 and ×4 SR tasks，the model is initialized with the pretrained weights from the ×2 model，and the total number of training iterations is reduced by half.
Result The proposed method is evaluated on five public benchmark datasets and compared with 11 state-of-the-art （SOTA） SR approaches. Experimental results demonstrate that under the constraint of lightweight design，SPSANet achieves either the best or second-best performance across different upscale factors and datasets，showing strong generalization ability and stability. Specifically，when the upscale factor is ×3，SPSANet surpasses the latest SOTA methods by 0.15 dB and 0.25 dB in peak signal-to-noise ratio （PSNR） on Urban100 and Manga109 datasets，respectively，and achieves corresponding improvements in the structural similarity index measure （SSIM）. Furthermore，when the self-ensemble strategy is applied during the testing phase，the model’s performance is further enhanced. Under the same scaling factor，PSNR increases by an additional 0.11 dB and 0.23 dB on Urban100 and Manga109，respectively，indicating that the proposed method maintains strong robustness under multiview inference. Ablation studies are conducted on SPSAM，HFEM，and DBFFM to further investigate the contribution of each component. The results show that removing any of these modules leads to a noticeable degradation in performance. SPSAM plays a key role in global dependency modeling and attention sparsification，HFEM effectively enhances texture restoration quality，and DBFFM substantially improves the fusion of global and local features. In terms of visual quality，SPSANet can reconstruct clear，natural，and sharp image textures，particularly in scenes with complex structures and abundant details. It preserves the structural consistency and perceptual realism of the original images more effectively than existing approaches do.
Conclusion In this work，we propose SPSANet，a lightweight image SR network that integrates an SPSA mechanism to efficiently capture long-range dependencies while minimizing redundant computations. By establishing interlayer attention connections，SPSANet enables focused feature learning，ensuring that the network prioritizes tokens that are the most critical to the reconstruction process. Moreover，the proposed HFEM enhances the recovery of fine textures and structural details，and DBFFM effectively aligns and integrates global and local representations. Through extensive experiments，SPSANet demonstrates superior reconstruction performance and visual fidelity compared with existing lightweight SR approaches，especially in challenging scenarios with intricate patterns and rich textures. Despite these promising results，opportunities for further improvement remain. Future work could enhance model compactness and generalization through knowledge distillation，hybrid convolution-Transformer integration，and adaptation to broad low-level vision tasks （e.g.，image denoising and deblurring）. Overall，SPSANet provides a practical，interpretable solution for lightweight Transformer-based image restoration，offering insights for the design of efficient and high-performing SR networks.
, authors=Siqi Wu, Wei Liu
*, Weidong Chen, authorsList=Siqi Wu, Wei Liu, Weidong Chen, authorCompany=null, correspAuthors=Wei Liu, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1322961088186287076, articleId=1322961075985056718, tenantId=1146029695717560320, journalId=1249024232475115590, language=CN, title=轻量级稀疏置换自注意力图像超分辨率网络, columnId=1322960981353181856, journalTitle=中国图象图形学报, columnName=图像处理和编码, runingTitle=null, highlight=null, articleAbstract=
目的 图像超分辨重建是计算机视觉领域一个典型低层视觉任务，能够为目标检测、图像分割等高层任务提供更清晰更结构化的输入。基于卷积神经网络（convolutional neural network，CNN）的图像超分辨率模型注重恢复图像的纹理和边缘信息，而基于Transformer的方法能建模全局上下文信息，但是存在注意力权重冗余问题。针对这两种模型的优缺点，设计了一种轻量级图像超分辨率网络。
方法 首先改进了传统的Transformer，提出了一种稀疏置换自注意力机制，在扩大窗口的同时解决冗余问题。在此基础上，基于CNN构建高频信息增强模块加强模型对局部细节信息的重建。在得到两种结构提取的特征后，提出一种双分支特征融合模块对全局特征和局部特征进行高效融合。
结果 本文方法在5个公开数据集上与11种先进超分辨方法进行了对比实验。结果表明，在保证模型轻量化的前提下，稀疏置换自注意力网络（sparse and permuted self-attention network，SPSANet）在不同放大倍率和数据集上均取得最优或次优性能。当放大倍率为3时，在Urban100和Manga109数据集上的峰值信噪比（peak signal-to-noise ratio，PSNR）分别较最新的SOTA（state of the art）方法提升了0.15 dB和0.28 dB。主观视觉效果显示，SPSANet在复杂纹理和细节丰富的场景中重建的图像更加清晰、自然。
结论 本文提出的轻量级稀疏置换自注意力图像超分辨率网络能够在保持较低参数量与计算复杂度的同时，在多个数据集上取得优异的重建效果，展现出良好的泛化性与应用价值。
, authors=吴思琪, 柳薇
*, 陈卫东, authorsList=吴思琪, 柳薇, 陈卫东, authorCompany=null, correspAuthors=柳薇, authorNote=
, correspAuthorsNote=
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=rjsgyxPqgegtNJcl9GV3/Q==, magXml=XSOQ7sVsEL+TiVZchoMjSw==, pdfUrl=null, pdf=cB27p1X37hpuxv85AKtndA==, pdfFileSize=5681296, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=NR/UKv1ruaEZG89kCK/teA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=0xbhv5RzDXOqTKnHZw4j/Q==, mapNumber=null, fund=null)}, authors=[Author(id=1322961089431995370, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=2024023468@m.scnu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322961091088745452, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, authorId=1322961089431995370, language=EN, stringName=Siqi Wu, firstName=Siqi, middleName=null, lastName=Wu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Computer Science，South China Normal University，Guangzhou 510631，China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961091503981549, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, authorId=1322961089431995370, language=CN, stringName=吴思琪, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=华南师范大学计算机学院，广州 510631, bio={"content":"
吴思琪，女，硕士研究生，主要研究方向为深度学习图像处理。E-mail： 2024023468@m.scnu.edu.cn
"}, bioImg=null, bioContent=
吴思琪，女，硕士研究生，主要研究方向为深度学习图像处理。E-mail： 2024023468@m.scnu.edu.cn
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961089037730790, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, xref=null, ext=[AuthorCompanyExt(id=1322961089050313703, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, companyId=1322961089037730790, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Computer Science，South China Normal University，Guangzhou 510631，China), AuthorCompanyExt(id=1322961089062896616, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, companyId=1322961089037730790, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=华南师范大学计算机学院，广州 510631)])]), Author(id=1322961091923411951, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=liuwei@m.scnu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322961092401562609, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, authorId=1322961091923411951, language=EN, stringName=Wei Liu, firstName=Wei, middleName=null, lastName=Liu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
*, address=School of Computer Science，South China Normal University，Guangzhou 510631，China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961092745495538, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, authorId=1322961091923411951, language=CN, stringName=柳薇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
*, address=华南师范大学计算机学院，广州 510631, bio={"content":"
柳薇，通信作者，女，副教授，主要研究方向为多媒体信息处理、机器学习。E-mail： liuwei@m.scnu.edu.cn
"}, bioImg=null, bioContent=
柳薇，通信作者，女，副教授，主要研究方向为多媒体信息处理、机器学习。E-mail： liuwei@m.scnu.edu.cn
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961089037730790, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, xref=null, ext=[AuthorCompanyExt(id=1322961089050313703, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, companyId=1322961089037730790, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Computer Science，South China Normal University，Guangzhou 510631，China), AuthorCompanyExt(id=1322961089062896616, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, companyId=1322961089037730790, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=华南师范大学计算机学院，广州 510631)])]), Author(id=1322961092841964532, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=chenwd@m.scnu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322961093223646198, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, authorId=1322961092841964532, language=EN, stringName=Weidong Chen, firstName=Weidong, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Computer Science，South China Normal University，Guangzhou 510631，China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961093370446839, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, authorId=1322961092841964532, language=CN, stringName=陈卫东, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=华南师范大学计算机学院，广州 510631, bio={"content":"
陈卫东，男，教授，主要研究方向为图论与复杂网络、组合优化、算法与计算复杂性。E-mail： chenwd@m.scnu.edu.cn
"}, bioImg=null, bioContent=
陈卫东，男，教授，主要研究方向为图论与复杂网络、组合优化、算法与计算复杂性。E-mail： chenwd@m.scnu.edu.cn
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961089037730790, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, xref=null, ext=[AuthorCompanyExt(id=1322961089050313703, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, companyId=1322961089037730790, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Computer Science，South China Normal University，Guangzhou 510631，China), AuthorCompanyExt(id=1322961089062896616, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, companyId=1322961089037730790, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=华南师范大学计算机学院，广州 510631)])])], keywords=[Keyword(id=1322961093672436728, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=EN, orderNo=1, keyword=deep learning), Keyword(id=1322961095723451385, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=EN, orderNo=2, keyword=image super-resolution), Keyword(id=1322961096100938746, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=EN, orderNo=3, keyword=sparse and permuted self-attention （SPSA）), Keyword(id=1322961096520369147, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=EN, orderNo=4, keyword=high-frequency information enhancement), Keyword(id=1322961096612643836, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=EN, orderNo=5, keyword=dual-branch feature fusion （DBFF）), Keyword(id=1322961096969159677, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=CN, orderNo=1, keyword=深度学习), Keyword(id=1322961097032074238, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=CN, orderNo=2, keyword=图像超分辨率), Keyword(id=1322961097380201471, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=CN, orderNo=3, keyword=稀疏置换自注意力（SPSA）), Keyword(id=1322961097459893248, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=CN, orderNo=4, keyword=高频信息增强), Keyword(id=1322961098231644160, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=CN, orderNo=5, keyword=双分支特征融合（DBFF）)], refs=[Reference(id=1322961119198969886, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=256, pageEnd=272, url=null, language=null, rfNumber=null, rfOrder=0, authorNames=Ahn N, Kang B, Sohn K A, journalName=null, refType=null, unstructuredReference=
Ahn N，
Kang B and
Sohn K A.
2018. Fast，accurate，and lightweight super-resolution with cascading residual network//Proceedings of the 15th European Conference on Computer Vision. Munich，Germany： Springer： 256-272 ［DOI：
10.1007/978-3-030-01249-6_16］, articleTitle=Fast，accurate，and lightweight super-resolution with cascading residual network, refAbstract=null), Reference(id=1322961119630983199, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2012, volume=null, issue=null, pageStart=#135, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=1, authorNames=Bevilacqua M, Roumy A, Guillemot C, Morel M L A, journalName=null, refType=null, unstructuredReference=
Bevilacqua M，
Roumy A，
Guillemot C and
Morel M L A.
2012. Low-complexity single-image super-resolution based on nonnegative neighbor embedding//Proceedings of 2012 British Machine Vision Conference. Surrey，UK： BMVA Press： #135 ［DOI：
10.5244/c.26.135］, articleTitle=Low-complexity single-image super-resolution based on nonnegative neighbor embedding, refAbstract=null), Reference(id=1322961120553730080, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2024, volume=29, issue=4, pageStart=875, pageEnd=889, url=null, language=null, rfNumber=null, rfOrder=2, authorNames=Bi X P, Chen S, Zhang L F, journalName=Journal of Image and Graphics, refType=null, unstructuredReference=
Bi X P，
Chen S and
Zhang L F.
2024. Blueprint separable convolution Transformer network for lightweight image super-resolution.
Journal of Image and Graphics，
29（4）： 875-889, articleTitle=Blueprint separable convolution Transformer network for lightweight image super-resolution, refAbstract=null), Reference(id=1322961122134982690, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2024, volume=29, issue=4, pageStart=875, pageEnd=889, url=null, language=null, rfNumber=null, rfOrder=3, authorNames=毕修平, 陈实, 张乐飞, journalName=中国图象图形学报, refType=null, unstructuredReference=毕修平，陈实，张乐飞.
2024. 轻量级图像超分辨率的蓝图可分离卷积Transformer网络.
中国图象图形学报，
29（4）： 875-889 ［DOI：
10.11834/jig.230225］, articleTitle=轻量级图像超分辨率的蓝图可分离卷积Transformer网络, refAbstract=null), Reference(id=1322961122554413091, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=5239, pageEnd=5249, url=null, language=null, rfNumber=null, rfOrder=4, authorNames=Chen Q, Wu Q M, Wang J, Hu Q H, Hu T, Ding E R, journalName=null, refType=null, unstructuredReference=
Chen Q，
Wu Q M，
Wang J，
Hu Q H，
Hu T，
Ding E R，
et al.
2022. MixFormer： mixing features across windows and dimensions//Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans，USA： IEEE： 5239-5249 ［DOI：
10.1109/CVPR52688.2022.00518］, articleTitle=MixFormer： mixing features across windows and dimensions, refAbstract=null), Reference(id=1322961122948677668, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2023a, volume=null, issue=null, pageStart=5896, pageEnd=5905, url=null, language=null, rfNumber=null, rfOrder=5, authorNames=Chen X, Li H, Li M Q, Pan J S, journalName=null, refType=null, unstructuredReference=
Chen X，
Li H，
Li M Q and
Pan J S.
2023a. Learning a sparse transformer network for effective image deraining//Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver，Canada： IEEE： 5896-5905 ［DOI：
10.1109/CVPR52729.2023.00571］, articleTitle=Learning a sparse transformer network for effective image deraining, refAbstract=null), Reference(id=1322961123783344166, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2023b, volume=null, issue=null, pageStart=12278, pageEnd=12287, url=null, language=null, rfNumber=null, rfOrder=6, authorNames=Chen Z, Zhang Y L, Gu J J, Kong L H, Yang X K, Yu F, journalName=null, refType=null, unstructuredReference=
Chen Z，
Zhang Y L，
Gu J J，
Kong L H，
Yang X K and
Yu F.
2023b. Dual aggregation transformer for image super-resolution//Proceedings of 2023 IEEE/CVF International Conference on Computer Vision. Paris，France： IEEE： 12278-12287 ［DOI：
10.1109/ICCV51070.2023.01131］, articleTitle=Dual aggregation transformer for image super-resolution, refAbstract=null), Reference(id=1322961123888201767, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=2071, pageEnd=2081, url=null, language=null, rfNumber=null, rfOrder=7, authorNames=Choi H, Lee J, Yang J, journalName=null, refType=null, unstructuredReference=
Choi H，
Lee J and
Yang J.
2023. N-Gram in swin Transformers for efficient lightweight image super-resolution//Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver，Canada： IEEE： 2071-2081 ［DOI：
10.1109/CVPR52729.2023.00206］, articleTitle=N-Gram in swin Transformers for efficient lightweight image super-resolution, refAbstract=null), Reference(id=1322961124253106216, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=184, pageEnd=199, url=null, language=null, rfNumber=null, rfOrder=8, authorNames=Dong C, Loy C C, He K M, Tang X O, journalName=null, refType=null, unstructuredReference=
Dong C，
Loy C C，
He K M and
Tang X O.
2014. Learning a deep convolutional network for image super-resolution//Proceedings of the 13th European Conference on Computer Vision. Zurich，Switzerland： Springer： 184-199 ［DOI：
10.1007/978-3-319-10593-2_13］, articleTitle=Learning a deep convolutional network for image super-resolution, refAbstract=null), Reference(id=1322961124336992297, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=913, pageEnd=919, url=null, language=null, rfNumber=null, rfOrder=9, authorNames=Gao G W, Wang Z X, Li J C, Li W J, Yu Y, Zeng T Y, journalName=null, refType=null, unstructuredReference=
Gao G W，
Wang Z X，
Li J C，
Li W J，
Yu Y and
Zeng T Y.
2022. Lightweight bimodal network for single-image super-resolution via symmetric CNN and recursive Transformer//Proceedings of the 31st International Joint Conference on Artificial Intelligence. Vienna，Austria： IJCAI.org： 913-919 ［DOI：
10.24963/ijcai.2022/128］, articleTitle=Lightweight bimodal network for single-image super-resolution via symmetric CNN and recursive Transformer, refAbstract=null), Reference(id=1322961124697702442, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=30, pageEnd=39, url=null, language=null, rfNumber=null, rfOrder=10, authorNames=Ghader H, Monz C, journalName=null, refType=null, unstructuredReference=
Ghader H and
Monz C.
2017. What does attention in neural machine translation pay attention to?//Proceedings of the 8th International Joint Conference on Natural Language Processing. Taipei，China： Asian Federation of Natural Language Processing： 30-39, articleTitle=What does attention in neural machine translation pay attention to?, refAbstract=null), Reference(id=1322961125075189803, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=518, pageEnd=522, url=null, language=null, rfNumber=null, rfOrder=11, authorNames=He Z B, Dai T, Lu J, Jiang Y, Xia S T, journalName=null, refType=null, unstructuredReference=
He Z B，
Dai T，
Lu J，
Jiang Y and
Xia S T.
2020. Fakd： feature-affinity based knowledge distillation for efficient image super-resolution//Proceedings of 2020 IEEE International Conference on Image Processing. Abu Dhabi，United Arab Emirates： IEEE： 518-522 ［DOI：
10.1109/ICIP40778.2020.9190917］, articleTitle=Fakd： feature-affinity based knowledge distillation for efficient image super-resolution, refAbstract=null), Reference(id=1322961126794854444, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=5197, pageEnd=5206, url=null, language=null, rfNumber=null, rfOrder=12, authorNames=Huang J B, Singh A, Ahuja N, journalName=null, refType=null, unstructuredReference=
Huang J B，
Singh A and
Ahuja N.
2015. Single image super-resolution from transformed self-exemplars//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston，USA： IEEE： 5197-5206 ［DOI：
10.1109/cvpr.2015.7299156］, articleTitle=Single image super-resolution from transformed self-exemplars, refAbstract=null), Reference(id=1322961127252033581, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=2024, pageEnd=2032, url=null, language=null, rfNumber=null, rfOrder=13, authorNames=Hui Z, Gao X B, Yang Y C, Wang X M, journalName=null, refType=null, unstructuredReference=
Hui Z，
Gao X B，
Yang Y C and
Wang X M.
2019. Lightweight image super-resolution with information multi-distillation network//Proceedings of the 27th ACM International Conference on Multimedia. Nice，France： Association for Computing Machinery： 2024-2032 ［DOI：
10.1145/3343031.3351084］, articleTitle=Lightweight image super-resolution with information multi-distillation network, refAbstract=null), Reference(id=1322961127583383598, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=723, pageEnd=731, url=null, language=null, rfNumber=null, rfOrder=14, authorNames=Hui Z, Wang X M, Gao X B, journalName=null, refType=null, unstructuredReference=
Hui Z，
Wang X M and
Gao X B.
2018. Fast and accurate single image super-resolution via information distillation network//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City，USA： IEEE： 723-731 ［DOI：
10.1109/CVPR.2018.00082］, articleTitle=Fast and accurate single image super-resolution via information distillation network, refAbstract=null), Reference(id=1322961127684046895, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=1646, pageEnd=1654, url=null, language=null, rfNumber=null, rfOrder=15, authorNames=Kim J, Lee J K, Lee K M, journalName=null, refType=null, unstructuredReference=
Kim J，
Lee J K and
Lee K M.
2016. Accurate image super-resolution using very deep convolutional networks//Proceedings of 2016 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Las Vegas，USA： IEEE： 1646-1654 ［DOI：
10.1109/CVPR.2016.182］, articleTitle=Accurate image super-resolution using very deep convolutional networks, refAbstract=null), Reference(id=1322961128095088688, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=24467, pageEnd=24477, url=null, language=null, rfNumber=null, rfOrder=16, authorNames=Lee D, Yun S, Ro Y, journalName=null, refType=null, unstructuredReference=
Lee D，
Yun S and
Ro Y.
2025. Emulating self-attention with convolution for efficient image super-resolution//Proceedings of 2025 IEEE/CVF International Conference on Computer Vision. Honolulu，USA： IEEE： 24467-24477, articleTitle=Emulating self-attention with convolution for efficient image super-resolution, refAbstract=null), Reference(id=1322961128506130481, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=12480, pageEnd=12490, url=null, language=null, rfNumber=null, rfOrder=17, authorNames=Li A, Zhang L, Liu Y, Zhu C, journalName=null, refType=null, unstructuredReference=
Li A，
Zhang L，
Liu Y and
Zhu C.
2023. Feature modulation transformer： cross-refinement of global representation via high-frequency prior for image super-resolution//Proceedings of 2023 IEEE/CVF International Conference on Computer Vision. Paris，France： IEEE： 12480-12490 ［DOI：
10.1109/ICCV51070.2023.01150］, articleTitle=Feature modulation transformer： cross-refinement of global representation via high-frequency prior for image super-resolution, refAbstract=null), Reference(id=1322961129235939378, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2025, volume=30, issue=3, pageStart=784, pageEnd=797, url=null, language=null, rfNumber=null, rfOrder=18, authorNames=Li Y, Dong S H, Zhang J W, Zhao R, Zheng Y H, journalName=Journal of Image and Graphics, refType=null, unstructuredReference=
Li Y，
Dong S H，
Zhang J W，
Zhao R and
Zheng Y H.
2025. Cross-scale Transformer image super-resolution reconstruction with fusion channel attention.
Journal of Image and Graphics，
30（3）： 784-797, articleTitle=Cross-scale Transformer image super-resolution reconstruction with fusion channel attention, refAbstract=null), Reference(id=1322961129693118515, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2025, volume=30, issue=3, pageStart=784, pageEnd=797, url=null, language=null, rfNumber=null, rfOrder=19, authorNames=李焱, 董仕豪, 张家伟, 赵茹, 郑钰辉, journalName=中国图象图形学报, refType=null, unstructuredReference=李焱，董仕豪，张家伟，赵茹，郑钰辉.
2025. 融合通道注意力的跨尺度Transformer图像超分辨率重建.
中国图象图形学报，
30（3）： 784-797 ［DOI：
10.11834/jig.240279］, articleTitle=融合通道注意力的跨尺度Transformer图像超分辨率重建, refAbstract=null), Reference(id=1322961131408588852, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=1833, pageEnd=1844, url=null, language=null, rfNumber=null, rfOrder=20, authorNames=Liang J Y, Cao J Z, Sun G L, Zhang K, van Gool L and Timofte R, journalName=null, refType=null, unstructuredReference=
Liang J Y，
Cao J Z，
Sun G L，
Zhang K，van Gool L and Timofte R.
2021. SwinIR： image restoration using swin transformer//Proceedings of 2021 IEEE/CVF International Conference on Computer Vision Workshops. Montreal，Canada： IEEE： 1833-1844 ［DOI：
10.1109/ICCVW54120.2021.00210］, articleTitle=SwinIR： image restoration using swin transformer, refAbstract=null), Reference(id=1322961131844796469, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=1132, pageEnd=1140, url=null, language=null, rfNumber=null, rfOrder=21, authorNames=Lim B, Son S, Kim H, Nah S, Lee K M, journalName=null, refType=null, unstructuredReference=
Lim B，
Son S，
Kim H，
Nah S and
Lee K M.
2017. Enhanced deep residual networks for single image super-resolution//Proceedings of 2022 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Honolulu，USA： IEEE： 1132-1140 ［DOI：
10.1109/CVPRW.2017.151］, articleTitle=Enhanced deep residual networks for single image super-resolution, refAbstract=null), Reference(id=1322961132247449654, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=2279, pageEnd=2288, url=null, language=null, rfNumber=null, rfOrder=22, authorNames=Long W, Zhou X Y, Zhang L H, Gu S H, journalName=null, refType=null, unstructuredReference=
Long W，
Zhou X Y，
Zhang L H and
Gu S H.
2025. Progressive focused transformer for single image super-resolution//Proceedings of 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville，USA： IEEE： 2279-2288 ［DOI：
10.1109/CVPR52734.2025.00218］, articleTitle=Progressive focused transformer for single image super-resolution, refAbstract=null), Reference(id=1322961132683657271, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=456, pageEnd=465, url=null, language=null, rfNumber=null, rfOrder=23, authorNames=Lu Z S, Li J C, Liu H, Huang C Y, Zhang L L, Zeng T Y, journalName=null, refType=null, unstructuredReference=
Lu Z S，
Li J C，
Liu H，
Huang C Y，
Zhang L L and
Zeng T Y.
2022. Transformer for single image super-resolution//Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. New Orleans，USA： IEEE： 456-465 ［DOI：
10.1109/CVPRW56347.2022.00061］, articleTitle=Transformer for single image super-resolution, refAbstract=null), Reference(id=1322961133073727544, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=272, pageEnd=289, url=null, language=null, rfNumber=null, rfOrder=24, authorNames=Luo X T, Xie Y, Zhang Y L, Qu Y Y, Li C H, Fu Y, journalName=null, refType=null, unstructuredReference=
Luo X T，
Xie Y，
Zhang Y L，
Qu Y Y，
Li C H and
Fu Y.
2020. LatticeNet： towards lightweight image super-resolution with lattice block//Proceedings of the 16th European Conference on Computer Vision. Glasgow，UK： Springer： 272-289 ［DOI：
10.1007/978-3-030-58542-6_17］, articleTitle=LatticeNet： towards lightweight image super-resolution with lattice block, refAbstract=null), Reference(id=1322961133929365561, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=25346, pageEnd=25358, url=null, language=null, rfNumber=null, rfOrder=25, authorNames=Mao M Y, Gao P, Zhang R R, Zheng H H, Ma T, Peng Y, journalName=null, refType=null, unstructuredReference=
Mao M Y，
Gao P，
Zhang R R，
Zheng H H，
Ma T，
Peng Y，
et al.
2021. Dual-stream network for visual recognition//Proceedings of the 35th International Conference on Neural Information Processing Systems. Red Hook，USA： Curran Associates Inc.： 25346-25358, articleTitle=Dual-stream network for visual recognition, refAbstract=null), Reference(id=1322961135145713723, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2001, volume=null, issue=null, pageStart=416, pageEnd=423, url=null, language=null, rfNumber=null, rfOrder=26, authorNames=Martin D, Fowlkes C, Tal D, Malik J, journalName=null, refType=null, unstructuredReference=
Martin D，
Fowlkes C，
Tal D and
Malik J.
2001. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics//Proceedings of the 8th IEEE International Conference on Computer Vision. Vancouver，Canada： IEEE： 416-423 ［DOI：
10.1109/iccv.2001.937655］, articleTitle=A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics, refAbstract=null), Reference(id=1322961135556755517, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2017, volume=76, issue=20, pageStart=21811, pageEnd=21838, url=null, language=null, rfNumber=null, rfOrder=27, authorNames=Matsui Y, Ito K, Aramaki Y, Fujimoto A, Ogawa T, Yamasaki T, journalName=Multimedia Tools and Applications, refType=null, unstructuredReference=
Matsui Y，
Ito K，
Aramaki Y，
Fujimoto A，
Ogawa T，
Yamasaki T，
et al.
2017. Sketch-based manga retrieval using manga109 dataset.
Multimedia Tools and Applications，
76（20）： 21811-21838 ［DOI：
10.1007/s11042-016-4020-z］, articleTitle=Sketch-based manga retrieval using manga109 dataset, refAbstract=null), Reference(id=1322961136009740350, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=357, pageEnd=366, url=null, language=null, rfNumber=null, rfOrder=28, authorNames=Peng Z L, Huang W, Gu S Z, Xie L X, Wang Y W, Jiao Y B, journalName=null, refType=null, unstructuredReference=
Peng Z L，
Huang W，
Gu S Z，
Xie L X，
Wang Y W，
Jiao Y B，
et al.
2021. Conformer： local features coupling global representations for visual recognition//Proceedings of 2021 IEEE/CVF International Conference on Computer Vision. Montreal，Canada： IEEE： 357-366 ［DOI：
10.1109/ICCV48922.2021.00042］, articleTitle=Conformer： local features coupling global representations for visual recognition, refAbstract=null), Reference(id=1322961136404004927, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2025, volume=30, issue=4, pageStart=1084, pageEnd=1099, url=null, language=null, rfNumber=null, rfOrder=29, authorNames=Song X G, Zhang P F, Liu W B, Lu X F, Hei X H, journalName=Journal of Image and Graphics, refType=null, unstructuredReference=
Song X G，
Zhang P F，
Liu W B，
Lu X F and
Hei X H.
2025. Image superresolution reconstruction based on multiscale large-kernel attention feature fusion network.
Journal of Image and Graphics，
30（4）： 1084-1099, articleTitle=Image superresolution reconstruction based on multiscale large-kernel attention feature fusion network, refAbstract=null), Reference(id=1322961137238671424, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2025, volume=30, issue=4, pageStart=1084, pageEnd=1099, url=null, language=null, rfNumber=null, rfOrder=30, authorNames=宋霄罡, 张鹏飞, 刘万波, 鲁晓锋, 黑新宏, journalName=中国图象图形学报, refType=null, unstructuredReference=宋霄罡，张鹏飞，刘万波，鲁晓锋，黑新宏.
2025. 多尺度大核注意力特征融合网络的图像超分辨率重建.
中国图象图形学报，
30（4）： 1084-1099 ［DOI：
10.11834/jig.240042］, articleTitle=多尺度大核注意力特征融合网络的图像超分辨率重建, refAbstract=null), Reference(id=1322961137645518913, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=22378, pageEnd=22387, url=null, language=null, rfNumber=null, rfOrder=31, authorNames=Wang H, Chen X H, Ni B B, Liu Y T, Liu J F, journalName=null, refType=null, unstructuredReference=
Wang H，
Chen X H，
Ni B B，
Liu Y T and
Liu J F.
2023. Omni aggregation networks for lightweight image super-resolution//Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver，Canada： IEEE： 22378-22387 ［DOI：
10.1109/CVPR52729.2023.02143］, articleTitle=Omni aggregation networks for lightweight image super-resolution, refAbstract=null), Reference(id=1322961138098503746, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2022, volume=27, issue=5, pageStart=1604, pageEnd=1615, url=null, language=null, rfNumber=null, rfOrder=32, authorNames=Wu H L, Li W Y, Zhang L B, journalName=Journal of Image and Graphics, refType=null, unstructuredReference=
Wu H L，
Li W Y and
Zhang L B.
2022. Cross-scale coupling network for continuous-scale image super-resolution.
Journal of Image and Graphics，
27（5）： 1604-1615, articleTitle=Cross-scale coupling network for continuous-scale image super-resolution, refAbstract=null), Reference(id=1322961138509545539, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2022, volume=27, issue=5, pageStart=1604, pageEnd=1615, url=null, language=null, rfNumber=null, rfOrder=33, authorNames=吴瀚霖, 李宛谕, 张立保, journalName=中国图象图形学报, refType=null, unstructuredReference=吴瀚霖，李宛谕，张立保.
2022. 跨尺度耦合的连续比例因子图像超分辨率.
中国图象图形学报，
27（5）： 1604-1615 ［DOI：
10.11834/jig.210815］, articleTitle=跨尺度耦合的连续比例因子图像超分辨率, refAbstract=null), Reference(id=1322961138903810116, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2012, volume=null, issue=null, pageStart=711, pageEnd=730, url=null, language=null, rfNumber=null, rfOrder=34, authorNames=Zeyde R, Elad M, Protter M, journalName=null, refType=null, unstructuredReference=
Zeyde R，
Elad M and
Protter M.
2012. On single image scale-up using sparse-representations//Proceedings of the 7th International Conference on Curves and Surfaces. Avignon，France： Springer： 711-730 ［DOI：
10.1007/978-3-642-27413-8_47］, articleTitle=On single image scale-up using sparse-representations, refAbstract=null), Reference(id=1322961140304707653, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2024a, volume=null, issue=null, pageStart=2856, pageEnd=2865, url=null, language=null, rfNumber=null, rfOrder=35, authorNames=Zhang L H, Li Y W, Zhou X Y, Zhao X R, Gu S H, journalName=null, refType=null, unstructuredReference=
Zhang L H，
Li Y W，
Zhou X Y，
Zhao X R and
Gu S H.
2024a. Transcending the limit of local window： advanced super-resolution transformer with adaptive token dictionary//Proceedings of 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle，USA： IEEE： 2856-2865 ［DOI：
10.1109/CVPR52733.2024.00276］, articleTitle=Transcending the limit of local window： advanced super-resolution transformer with adaptive token dictionary, refAbstract=null), Reference(id=1322961140610891846, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2024b, volume=null, issue=null, pageStart=483, pageEnd=500, url=null, language=null, rfNumber=null, rfOrder=36, authorNames=Zhang X, Zhang Y L, Yu F, journalName=null, refType=null, unstructuredReference=
Zhang X，
Zhang Y L and
Yu F.
2024b. HiT-SR： hierarchical transformer for efficient image super-resolution//Proceedings of the 18th European Conference on Computer Vision. Milan，Italy： Springer： 483-500 ［DOI：
10.1007/978-3-031-73661-2_27］, articleTitle=HiT-SR： hierarchical transformer for efficient image super-resolution, refAbstract=null), Reference(id=1322961141055488071, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=649, pageEnd=667, url=null, language=null, rfNumber=null, rfOrder=37, authorNames=Zhang X D, Zeng H, Guo S, Zhang L, journalName=null, refType=null, unstructuredReference=
Zhang X D，
Zeng H，
Guo S and
Zhang L.
2022. Efficient long-range attention network for image super-resolution//Proceedings of the 17th European Conference on Computer Vision. Tel Aviv，Israel： Springer： 649-667 ［DOI：
10.1007/978-3-031-19790-1_39］, articleTitle=Efficient long-range attention network for image super-resolution, refAbstract=null), Reference(id=1322961141432975432, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=12734, pageEnd=12745, url=null, language=null, rfNumber=null, rfOrder=38, authorNames=Zhou Y P, Li Z, Guo C L, Bai S, Chen M M, Hou Q B, journalName=null, refType=null, unstructuredReference=
Zhou Y P，
Li Z，
Guo C L，
Bai S，
Chen M M and
Hou Q B.
2023. SRFormer： permuted self-attention for single image super-resolution//Proceedings of 2023 IEEE/CVF International Conference on Computer Vision. Paris，France： IEEE： 12734-12745 ［DOI：
10.1109/ICCV51070.2023.01174］, articleTitle=SRFormer： permuted self-attention for single image super-resolution, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1322961089037730790, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, xref=null, ext=[AuthorCompanyExt(id=1322961089050313703, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, companyId=1322961089037730790, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Computer Science，South China Normal University，Guangzhou 510631，China), AuthorCompanyExt(id=1322961089062896616, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, companyId=1322961089037730790, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=华南师范大学计算机学院，广州 510631)])], figs=[ArticleFig(id=1322961100374933505, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=EN, label=Fig.1, caption=
Cosine similarity calculated based on Urban100（（a）×2 cosine similarity；（b）×4 cosine similarity）, figureFileSmall=LuYdFi6ACaEOwpsvi8UKPw==, figureFileBig=NR/UKv1ruaEZG89kCK/teA==, tableContent=null), ArticleFig(id=1322961100739837954, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=CN, label=图1, caption=
基于Urban100计算的余弦相似度, figureFileSmall=LuYdFi6ACaEOwpsvi8UKPw==, figureFileBig=NR/UKv1ruaEZG89kCK/teA==, tableContent=null), ArticleFig(id=1322961101993934852, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=EN, label=Fig.2, caption=
Network architecture, figureFileSmall=P1RvaP4wd1t7HCj6fUPWuQ==, figureFileBig=wIzLSzDr2uYTa6ylfs/MRQ==, tableContent=null), ArticleFig(id=1322961102895710213, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=CN, label=图2, caption=
网络结构, figureFileSmall=P1RvaP4wd1t7HCj6fUPWuQ==, figureFileBig=wIzLSzDr2uYTa6ylfs/MRQ==, tableContent=null), ArticleFig(id=1322961104518905862, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=EN, label=Fig.3, caption=
Sparse permuted self-attention block（（a）SPSA；（b）high-freguency in formation enhancement；（c）DBFF；（d）C-I；（e）S-I）, figureFileSmall=MKfTXTuzTOm69ahXaIGLZg==, figureFileBig=cdRCZ51VDI3nLmB19q7HXg==, tableContent=null), ArticleFig(id=1322961105374543879, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=CN, label=图3, caption=
稀疏置换注意力块, figureFileSmall=MKfTXTuzTOm69ahXaIGLZg==, figureFileBig=cdRCZ51VDI3nLmB19q7HXg==, tableContent=null), ArticleFig(id=1322961105777197064, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=EN, label=Fig.4, caption=
Compression permutation operation, figureFileSmall=jqtS2x1s0G11/xtz5NX91A==, figureFileBig=VS9EaokJF9UITNwFnkbw7Q==, tableContent=null), ArticleFig(id=1322961106192433161, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=CN, label=图4, caption=
压缩置换操作, figureFileSmall=jqtS2x1s0G11/xtz5NX91A==, figureFileBig=VS9EaokJF9UITNwFnkbw7Q==, tableContent=null), ArticleFig(id=1322961106595086346, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=EN, label=Fig.5, caption=
Comparison of super-resolution visualization at different magnifications on Urban100, figureFileSmall=VIQK2wkG322OG/CLus7EAg==, figureFileBig=RGSeutp2CYXkI6S34xm1mA==, tableContent=null), ArticleFig(id=1322961107043876875, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=CN, label=图5, caption=
Urban100上不同放大倍数超分辨率可视化对比, figureFileSmall=VIQK2wkG322OG/CLus7EAg==, figureFileBig=RGSeutp2CYXkI6S34xm1mA==, tableContent=null), ArticleFig(id=1322961108721598476, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=EN, label=Fig.6, caption=
Comparison of entropy values at each layer of different attention mechanisms, figureFileSmall=ECAKiTticPtkRpeiyEhh1w==, figureFileBig=zDbMDUdJuFd9iMS5HE3hYA==, tableContent=null), ArticleFig(id=1322961109195554829, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=CN, label=图6, caption=
不同注意力机制各层的熵值对比, figureFileSmall=ECAKiTticPtkRpeiyEhh1w==, figureFileBig=zDbMDUdJuFd9iMS5HE3hYA==, tableContent=null), ArticleFig(id=1322961109975695374, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=EN, label=Fig.7, caption=
Comparison of feature maps of different branches （（a） LR image； （b） feature map of Conv； （c） feature map of Transformer）, figureFileSmall=0cDgmTPi4vFAHJNV9CCHcQ==, figureFileBig=AiTDglr5S2uJW1xX2qY7hA==, tableContent=null), ArticleFig(id=1322961110424485903, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=CN, label=图7, caption=
不同分支特征图对比, figureFileSmall=0cDgmTPi4vFAHJNV9CCHcQ==, figureFileBig=AiTDglr5S2uJW1xX2qY7hA==, tableContent=null), ArticleFig(id=1322961110818750480, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=EN, label=Fig.8, caption=
LAM comparison results, figureFileSmall=y64RiIkp8DLMMZ76zyFVuQ==, figureFileBig=HFMkMCV6HciR/SD5akM6pg==, tableContent=null), ArticleFig(id=1322961111242375185, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=CN, label=图8, caption=
LAM比较结果, figureFileSmall=y64RiIkp8DLMMZ76zyFVuQ==, figureFileBig=HFMkMCV6HciR/SD5akM6pg==, tableContent=null), ArticleFig(id=1322961111670194194, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=EN, label=Table 1, caption=
Results of objective results of ×2 super-resolution for different methods, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 参数量/k | Mult- Adds/G | Set5 | Set14 | BSD100 | Urban100 | Manage109 |
|---|
PSNR /dB | SSIM | PSNR /dB | SSIM | PSNR /dB | SSIM | PSNR /dB | SSIM | PSNR /dB | SSIM |
|---|
| EDSR（Lim等，2017） | 1 370 | 316.3 | 37.99 | 0.960 4 | 33.57 | 0.917 5 | 32.16 | 0.899 4 | 31.98 | 0.927 2 | 38.54 | 0.976 9 |
| CARN（Ahn等，2018） | 1 592 | 222.8 | 37.76 | 0.959 0 | 33.52 | 0.916 6 | 32.09 | 0.897 8 | 31.92 | 0.925 6 | 38.36 | 0.976 5 |
| IMDN（Hui等，2019） | 694 | 158.8 | 38.00 | 0.960 5 | 33.63 | 0.917 7 | 32.19 | 0.899 6 | 32.17 | 0.928 3 | 38.88 | 0.977 4 |
| LatticeNet（Luo等，2020） | 756 | 169.5 | 38.06 | 0.960 7 | 33.70 | 0.918 7 | 32.20 | 0.899 9 | 32.25 | 0.928 8 | - | - |
| SwinIR-It（Liang等，2021） | 878 | 195.6 | 38.14 | 0.961 1 | 33.86 | 0.920 6 | 32.31 | 0.901 2 | 32.76 | 0.934 0 | 39.12 | 0.978 3 |
| LBNet（Gao等，2022） | 731 | 153.2 | 38.05 | 0.960 7 | 33.65 | 0.917 7 | 32.16 | 0.899 4 | 32.30 | 0.929 1 | 38.88 | 0.977 5 |
| ESRT（Lu等，2022） | 677 | 191.4 | 38.03 | 0.960 0 | 33.75 | 0.918 4 | 32.25 | 0.900 1 | 32.58 | 0.931 8 | 39.12 | 0.977 4 |
| SwinIR-NG（Choi等，2023） | 1 181 | 274.1 | 38.17 | 0.961 2 | 33.94 | 0.920 5 | 32.31 | 0.901 3 | 32.78 | 0.934 0 | 39.20 | 0.978 5 |
| SRFormer-It（Zhou等，2023） | 853 | 197.5 | 38.23 | 0.961 3 | 33.94 | 0.920 9 | 32.36 | 0.901 9 | 32.91 | 0.935 3 | 39.28 | 0.978 5 |
| BSTN（毕修平 等，2024） | 736 | 163.6 | 38.17 | 0.961 6 | 33.87 | 0.920 1 | 32.28 | 0.901 0 | 32.60 | 0.931 8 | - | - |
| MLFN-L（宋霄罡 等，2025） | 1 071 | - | 38.15 | 0.961 2 | 33.85 | 0.919 7 | 32.33 | 0.901 3 | 32.58 | 0.933 1 | 39.06 | 0.978 2 |
| SPSANet（本文） | 1 063 | 247.0 | 38.25 | 0.961 6 | 33.95 | 0.921 4 | 32.35 | 0.902 0 | 32.99 | 0.936 3 | 39.34 | 0.978 7 |
| SPSANet+（本文） | 1 063 | 247.0 | 38.28 | 0.961 7 | 34.02 | 0.921 7 | 32.38 | 0.902 3 | 33.14 | 0.937 2 | 39.48 | 0.979 0 |
), ArticleFig(id=1322961113322749972, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=CN, label=表1, caption=
不同方法的2倍超分辨率客观评价结果
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 参数量/k | Mult- Adds/G | Set5 | Set14 | BSD100 | Urban100 | Manage109 |
|---|
PSNR /dB | SSIM | PSNR /dB | SSIM | PSNR /dB | SSIM | PSNR /dB | SSIM | PSNR /dB | SSIM |
|---|
| EDSR（Lim等，2017） | 1 370 | 316.3 | 37.99 | 0.960 4 | 33.57 | 0.917 5 | 32.16 | 0.899 4 | 31.98 | 0.927 2 | 38.54 | 0.976 9 |
| CARN（Ahn等，2018） | 1 592 | 222.8 | 37.76 | 0.959 0 | 33.52 | 0.916 6 | 32.09 | 0.897 8 | 31.92 | 0.925 6 | 38.36 | 0.976 5 |
| IMDN（Hui等，2019） | 694 | 158.8 | 38.00 | 0.960 5 | 33.63 | 0.917 7 | 32.19 | 0.899 6 | 32.17 | 0.928 3 | 38.88 | 0.977 4 |
| LatticeNet（Luo等，2020） | 756 | 169.5 | 38.06 | 0.960 7 | 33.70 | 0.918 7 | 32.20 | 0.899 9 | 32.25 | 0.928 8 | - | - |
| SwinIR-It（Liang等，2021） | 878 | 195.6 | 38.14 | 0.961 1 | 33.86 | 0.920 6 | 32.31 | 0.901 2 | 32.76 | 0.934 0 | 39.12 | 0.978 3 |
| LBNet（Gao等，2022） | 731 | 153.2 | 38.05 | 0.960 7 | 33.65 | 0.917 7 | 32.16 | 0.899 4 | 32.30 | 0.929 1 | 38.88 | 0.977 5 |
| ESRT（Lu等，2022） | 677 | 191.4 | 38.03 | 0.960 0 | 33.75 | 0.918 4 | 32.25 | 0.900 1 | 32.58 | 0.931 8 | 39.12 | 0.977 4 |
| SwinIR-NG（Choi等，2023） | 1 181 | 274.1 | 38.17 | 0.961 2 | 33.94 | 0.920 5 | 32.31 | 0.901 3 | 32.78 | 0.934 0 | 39.20 | 0.978 5 |
| SRFormer-It（Zhou等，2023） | 853 | 197.5 | 38.23 | 0.961 3 | 33.94 | 0.920 9 | 32.36 | 0.901 9 | 32.91 | 0.935 3 | 39.28 | 0.978 5 |
| BSTN（毕修平 等，2024） | 736 | 163.6 | 38.17 | 0.961 6 | 33.87 | 0.920 1 | 32.28 | 0.901 0 | 32.60 | 0.931 8 | - | - |
| MLFN-L（宋霄罡 等，2025） | 1 071 | - | 38.15 | 0.961 2 | 33.85 | 0.919 7 | 32.33 | 0.901 3 | 32.58 | 0.933 1 | 39.06 | 0.978 2 |
| SPSANet（本文） | 1 063 | 247.0 | 38.25 | 0.961 6 | 33.95 | 0.921 4 | 32.35 | 0.902 0 | 32.99 | 0.936 3 | 39.34 | 0.978 7 |
| SPSANet+（本文） | 1 063 | 247.0 | 38.28 | 0.961 7 | 34.02 | 0.921 7 | 32.38 | 0.902 3 | 33.14 | 0.937 2 | 39.48 | 0.979 0 |
), ArticleFig(id=1322961113805094933, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=EN, label=Table 2, caption=
Results of objective results of ×3 super-resolution for different methods, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 参数量/k | Mult- Adds/G | Set5 | Set14 | BSD100 | Urban100 | Manage109 |
|---|
PSNR /dB | SSIM | PSNR /dB | SSIM | PSNR /dB | SSIM | PSNR /dB | SSIM | PSNR /dB | SSIM |
|---|
| EDSR（Lim等，2017） | 1 555 | 160.2 | 34.37 | 0.927 0 | 30.28 | 0.841 7 | 29.09 | 0.805 2 | 28.15 | 0.852 7 | 33.45 | 0.943 9 |
| CARN（Ahn等，2018） | 1 592 | 118.8 | 34.29 | 0.925 5 | 30.29 | 0.840 7 | 29.06 | 0.803 4 | 28.06 | 0.849 3 | 33.50 | 0.944 0 |
| IMDN（Hui等，2019） | 703 | 71.5 | 34.36 | 0.927 0 | 30.32 | 0.841 7 | 29.09 | 0.804 6 | 28.17 | 0.851 9 | 33.61 | 0.944 5 |
| LatticeNet（Luo等，2020） | 765 | 76.3 | 34.53 | 0.928 1 | 30.39 | 0.842 4 | 29.15 | 0.805 9 | 28.33 | 0.853 8 | - | - |
| SwinIR-It（Liang等，2021） | 886 | 87.2 | 34.62 | 0.928 9 | 30.54 | 0.846 3 | 29.20 | 0.808 2 | 28.66 | 0.862 4 | 33.98 | 0.947 8 |
| LBNet（Gao等，2022） | 736 | 68.4 | 34.47 | 0.927 7 | 30.38 | 0.841 7 | 29.13 | 0.806 1 | 28.42 | 0.855 9 | 33.82 | 0.946 0 |
| ESRT（Lu等，2022） | 770 | 96.4 | 34.42 | 0.926 8 | 30.43 | 0.843 3 | 29.15 | 0.806 3 | 28.46 | 0.857 4 | 33.95 | 0.945 5 |
| SwinIR-NG（Choi等，2023） | 1 190 | 114.1 | 34.64 | 0.929 3 | 30.58 | 0.847 1 | 29.24 | 0.809 0 | 28.75 | 0.863 9 | 34.22 | 0.948 8 |
| SRFormer-It（Zhou等，2023） | 862 | 87.8 | 34.67 | 0.929 6 | 30.57 | 0.846 9 | 29.26 | 0.809 9 | 28.81 | 0.865 5 | 34.19 | 0.948 9 |
| BSTN（毕修平 等，2024） | 736 | 72.2 | 34.68 | 0.929 6 | 30.54 | 0.845 1 | 29.23 | 0.808 1 | 28.62 | 0.860 4 | - | - |
| MLFN-L（宋霄罡 等，2025） | 1 079 | - | 34.63 | 0.929 2 | 30.55 | 0.846 4 | 29.24 | 0.807 7 | 28.69 | 0.862 7 | 34.05 | 0.948 1 |
| SPSANet（本文） | 1 071 | 108.8 | 34.67 | 0.930 0 | 30.56 | 0.848 4 | 29.27 | 0.810 3 | 28.96 | 0.868 9 | 34.47 | 0.950 0 |
| SPSANet+（本文） | 1 071 | 108.8 | 34.76 | 0.930 5 | 30.57 | 0.849 2 | 29.32 | 0.811 1 | 29.10 | 0.870 7 | 34.64 | 0.951 0 |
), ArticleFig(id=1322961114237108246, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=CN, label=表2, caption=
不同方法的3倍超分辨率客观评价结果
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 参数量/k | Mult- Adds/G | Set5 | Set14 | BSD100 | Urban100 | Manage109 |
|---|
PSNR /dB | SSIM | PSNR /dB | SSIM | PSNR /dB | SSIM | PSNR /dB | SSIM | PSNR /dB | SSIM |
|---|
| EDSR（Lim等，2017） | 1 555 | 160.2 | 34.37 | 0.927 0 | 30.28 | 0.841 7 | 29.09 | 0.805 2 | 28.15 | 0.852 7 | 33.45 | 0.943 9 |
| CARN（Ahn等，2018） | 1 592 | 118.8 | 34.29 | 0.925 5 | 30.29 | 0.840 7 | 29.06 | 0.803 4 | 28.06 | 0.849 3 | 33.50 | 0.944 0 |
| IMDN（Hui等，2019） | 703 | 71.5 | 34.36 | 0.927 0 | 30.32 | 0.841 7 | 29.09 | 0.804 6 | 28.17 | 0.851 9 | 33.61 | 0.944 5 |
| LatticeNet（Luo等，2020） | 765 | 76.3 | 34.53 | 0.928 1 | 30.39 | 0.842 4 | 29.15 | 0.805 9 | 28.33 | 0.853 8 | - | - |
| SwinIR-It（Liang等，2021） | 886 | 87.2 | 34.62 | 0.928 9 | 30.54 | 0.846 3 | 29.20 | 0.808 2 | 28.66 | 0.862 4 | 33.98 | 0.947 8 |
| LBNet（Gao等，2022） | 736 | 68.4 | 34.47 | 0.927 7 | 30.38 | 0.841 7 | 29.13 | 0.806 1 | 28.42 | 0.855 9 | 33.82 | 0.946 0 |
| ESRT（Lu等，2022） | 770 | 96.4 | 34.42 | 0.926 8 | 30.43 | 0.843 3 | 29.15 | 0.806 3 | 28.46 | 0.857 4 | 33.95 | 0.945 5 |
| SwinIR-NG（Choi等，2023） | 1 190 | 114.1 | 34.64 | 0.929 3 | 30.58 | 0.847 1 | 29.24 | 0.809 0 | 28.75 | 0.863 9 | 34.22 | 0.948 8 |
| SRFormer-It（Zhou等，2023） | 862 | 87.8 | 34.67 | 0.929 6 | 30.57 | 0.846 9 | 29.26 | 0.809 9 | 28.81 | 0.865 5 | 34.19 | 0.948 9 |
| BSTN（毕修平 等，2024） | 736 | 72.2 | 34.68 | 0.929 6 | 30.54 | 0.845 1 | 29.23 | 0.808 1 | 28.62 | 0.860 4 | - | - |
| MLFN-L（宋霄罡 等，2025） | 1 079 | - | 34.63 | 0.929 2 | 30.55 | 0.846 4 | 29.24 | 0.807 7 | 28.69 | 0.862 7 | 34.05 | 0.948 1 |
| SPSANet（本文） | 1 071 | 108.8 | 34.67 | 0.930 0 | 30.56 | 0.848 4 | 29.27 | 0.810 3 | 28.96 | 0.868 9 | 34.47 | 0.950 0 |
| SPSANet+（本文） | 1 071 | 108.8 | 34.76 | 0.930 5 | 30.57 | 0.849 2 | 29.32 | 0.811 1 | 29.10 | 0.870 7 | 34.64 | 0.951 0 |
), ArticleFig(id=1322961114979500055, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=EN, label=Table 3, caption=
Results of objective results of ×4 super-resolution for different methods, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 参数量/k | Mult- Adds/G | Set5 | Set14 | BSD100 | Urban100 | Manage109 |
|---|
PSNR /dB | SSIM | PSNR /dB | SSIM | PSNR /dB | SSIM | PSNR /dB | SSIM | PSNR /dB | SSIM |
|---|
| EDSR（Lim等，2017） | 1 518 | 114.0 | 32.09 | 0.893 8 | 28.58 | 0.781 3 | 27.57 | 0.735 7 | 26.04 | 0.784 9 | 30.35 | 0.906 7 |
| CARN（Ahn等，2018） | 1 592 | 90.0 | 32.13 | 0.893 7 | 28.60 | 0.780 6 | 27.58 | 0.734 9 | 26.07 | 0.783 7 | 30.47 | 0.908 4 |
| IMDN（Hui等，2019） | 752 | 40.9 | 32.21 | 0.894 8 | 28.58 | 0.781 1 | 27.56 | 0.735 3 | 26.04 | 0.783 8 | 30.45 | 0.907 5 |
| LatticeNet（Luo等，2020） | 777 | 43.6 | 32.18 | 0.894 3 | 28.61 | 0.781 2 | 27.57 | 0.735 5 | 26.14 | 0.784 4 | - | - |
| SwinIR-It（Liang等，2021） | 897 | 49.6 | 32.44 | 0.897 6 | 28.77 | 0.785 8 | 27.69 | 0.740 6 | 26.47 | 0.798 0 | 30.92 | 0.915 1 |
| LBNet（Gao等，2022） | 742 | 38.9 | 32.29 | 0.896 0 | 28.68 | 0.783 2 | 27.62 | 0.738 2 | 26.27 | 0.790 6 | 30.76 | 0.911 1 |
| ESRT（Lu等，2022） | 751 | 67.7 | 32.19 | 0.894 7 | 28.69 | 0.783 3 | 27.69 | 0.737 9 | 26.39 | 0.796 2 | 30.75 | 0.910 0 |
| SwinIR-NG（Choi等，2023） | 1 201 | 63.0 | 32.44 | 0.898 0 | 28.83 | 0.787 0 | 27.73 | 0.741 8 | 26.61 | 0.801 0 | 31.09 | 0.916 1 |
| SRFormer-It（Zhou等，2023） | 873 | 52.7 | 32.51 | 0.898 8 | 28.82 | 0.787 2 | 27.73 | 0.742 2 | 26.67 | 0.803 2 | 31.17 | 0.916 5 |
| BSTN（毕修平 等，2024） | 751 | 41.8 | 32.50 | 0.898 5 | 28.78 | 0.785 2 | 27.71 | 0.740 3 | 26.49 | 0.796 5 | - | - |
| MLFN-L（宋霄罡 等，2025） | 1 071 | - | 32.37 | 0.897 5 | 28.85 | 0.786 4 | 27.73 | 0.741 0 | 26.52 | 0.798 5 | 30.95 | 0.915 3 |
| SPSANet（本文） | 1 082 | 65.1 | 32.39 | 0.899 2 | 28.70 | 0.788 8 | 27.74 | 0.743 2 | 26.80 | 0.808 3 | 31.33 | 0.918 3 |
| SPSANet+（本文） | 1 082 | 65.1 | 32.51 | 0.900 2 | 28.72 | 0.789 9 | 27.79 | 0.744 1 | 26.91 | 0.810 3 | 31.56 | 0.920 2 |
), ArticleFig(id=1322961115084357656, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=CN, label=表3, caption=
不同方法的4倍超分辨率客观评价结果
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 参数量/k | Mult- Adds/G | Set5 | Set14 | BSD100 | Urban100 | Manage109 |
|---|
PSNR /dB | SSIM | PSNR /dB | SSIM | PSNR /dB | SSIM | PSNR /dB | SSIM | PSNR /dB | SSIM |
|---|
| EDSR（Lim等，2017） | 1 518 | 114.0 | 32.09 | 0.893 8 | 28.58 | 0.781 3 | 27.57 | 0.735 7 | 26.04 | 0.784 9 | 30.35 | 0.906 7 |
| CARN（Ahn等，2018） | 1 592 | 90.0 | 32.13 | 0.893 7 | 28.60 | 0.780 6 | 27.58 | 0.734 9 | 26.07 | 0.783 7 | 30.47 | 0.908 4 |
| IMDN（Hui等，2019） | 752 | 40.9 | 32.21 | 0.894 8 | 28.58 | 0.781 1 | 27.56 | 0.735 3 | 26.04 | 0.783 8 | 30.45 | 0.907 5 |
| LatticeNet（Luo等，2020） | 777 | 43.6 | 32.18 | 0.894 3 | 28.61 | 0.781 2 | 27.57 | 0.735 5 | 26.14 | 0.784 4 | - | - |
| SwinIR-It（Liang等，2021） | 897 | 49.6 | 32.44 | 0.897 6 | 28.77 | 0.785 8 | 27.69 | 0.740 6 | 26.47 | 0.798 0 | 30.92 | 0.915 1 |
| LBNet（Gao等，2022） | 742 | 38.9 | 32.29 | 0.896 0 | 28.68 | 0.783 2 | 27.62 | 0.738 2 | 26.27 | 0.790 6 | 30.76 | 0.911 1 |
| ESRT（Lu等，2022） | 751 | 67.7 | 32.19 | 0.894 7 | 28.69 | 0.783 3 | 27.69 | 0.737 9 | 26.39 | 0.796 2 | 30.75 | 0.910 0 |
| SwinIR-NG（Choi等，2023） | 1 201 | 63.0 | 32.44 | 0.898 0 | 28.83 | 0.787 0 | 27.73 | 0.741 8 | 26.61 | 0.801 0 | 31.09 | 0.916 1 |
| SRFormer-It（Zhou等，2023） | 873 | 52.7 | 32.51 | 0.898 8 | 28.82 | 0.787 2 | 27.73 | 0.742 2 | 26.67 | 0.803 2 | 31.17 | 0.916 5 |
| BSTN（毕修平 等，2024） | 751 | 41.8 | 32.50 | 0.898 5 | 28.78 | 0.785 2 | 27.71 | 0.740 3 | 26.49 | 0.796 5 | - | - |
| MLFN-L（宋霄罡 等，2025） | 1 071 | - | 32.37 | 0.897 5 | 28.85 | 0.786 4 | 27.73 | 0.741 0 | 26.52 | 0.798 5 | 30.95 | 0.915 3 |
| SPSANet（本文） | 1 082 | 65.1 | 32.39 | 0.899 2 | 28.70 | 0.788 8 | 27.74 | 0.743 2 | 26.80 | 0.808 3 | 31.33 | 0.918 3 |
| SPSANet+（本文） | 1 082 | 65.1 | 32.51 | 0.900 2 | 28.72 | 0.789 9 | 27.79 | 0.744 1 | 26.91 | 0.810 3 | 31.56 | 0.920 2 |
), ArticleFig(id=1322961115877081114, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=EN, label=Table 4, caption=
Comparison of result with different model settings on Urban100（×2） dataset, figureFileSmall=null, figureFileBig=null, tableContent=
| 基线 | 稀疏置换注意力 | 高频信息增强 | 拼接加卷积 | 双分支特征融合 | 参数量/k | Mult-Adds/G | PSNR/dB | SSIM |
|---|
| √ | - | - | - | - | 853 | 197.5 | 32.52 | 0.932 2 |
| √ | √ | - | - | - | 853 | 197.5 | 32.63 | 0.933 2 |
| √ | √ | √ | √ | - | 1 218 | 284.0 | 32.74 | 0.934 0 |
| √ | √ | √ | - | √ | 1 063 | 247.0 | 32.79 | 0.934 3 |
), ArticleFig(id=1322961117961650205, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961075985056718, language=CN, label=表4, caption=
不同模型在Urban100（×2）数据集的结果对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 基线 | 稀疏置换注意力 | 高频信息增强 | 拼接加卷积 | 双分支特征融合 | 参数量/k | Mult-Adds/G | PSNR/dB | SSIM |
|---|
| √ | - | - | - | - | 853 | 197.5 | 32.52 | 0.932 2 |
| √ | √ | - | - | - | 853 | 197.5 | 32.63 | 0.933 2 |
| √ | √ | √ | √ | - | 1 218 | 284.0 | 32.74 | 0.934 0 |
| √ | √ | √ | - | √ | 1 063 | 247.0 | 32.79 | 0.934 3 |
)], attaches=null, journal=Journal(id=1249023527618129992, delFlag=0, nameCn=中国图象图形学报, nameEn=Journal of Image and Graphics, nameHistory1=null, nameHistory2=null, issn=1006-8961, eissn=null, cn=11-3758, coden=CODEN ZTTXFZ, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=uirXtX858YS3zEpFXZttJA==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Image and Graphics, journalRemark=null, publicationField=null, createdTime=1775720014721, updatedTime=1788951488513, createdBy=18614031015, updatedBy=13041195026, firstLetterCn=Z, firstLetterEn=Z, subjectCode=Electronic Information, subjectName=null, subjectCodeEn=Electronic Information, subjectNameEn=null, picCn=uirXtX858YS3zEpFXZttJA==, picEn=bud7qaxfvWHeFsbyBTAiKQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1304520351199814396, language=CN, name=中国图象图形学报, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788951488542, updatedTime=1788951488542, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-cjig-author&redirect_uri=https%3A%2F%2Fcjig.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=e6369def-2842-41d8, submissionEditorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-cjig-editor&redirect_uri=https%3A%2F%2Fcjigeditor.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=9ccec05b-6bd, submissionReviewUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-cjig-author&redirect_uri=https%3A%2F%2Fcjig.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=1e8a31c8-5434-4f78, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1304520351250146045, language=EN, name=Journal of Image and Graphics, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788951488554, updatedTime=1788951488554, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-cjig-author&redirect_uri=https%3A%2F%2Fcjig.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=e6369def-2842-41d8, submissionEditorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-cjig-editor&redirect_uri=https%3A%2F%2Fcjigeditor.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=9ccec05b-6bd, submissionReviewUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-cjig-author&redirect_uri=https%3A%2F%2Fcjig.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=1e8a31c8-5434-4f78, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1249024232475115590, websiteList=[Website(id=1249025782459334881, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1249024232475115590, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN, language=CN, createTime=1775720552315, createBy=18614031015, updateTime=1775720586268, updateBy=18614031015, name=中国图象图形学报-中文, tplId=1146099689490845704, title=中国图象图形学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1249026166254928133, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=articleTextType, value=kx, createTime=1775720643819, updateTime=1775720643819, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166221373698, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=banner, value=null, createTime=1775720643811, updateTime=1775720643811, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166271705352, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=grayFlag, value=0, createTime=1775720643823, updateTime=1775720643823, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166212985089, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=logo, value=https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN/file/pic?fileId=TDRjKTHfgAnvFKZaDA70wA==, createTime=1775720643809, updateTime=1775720643809, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166288482570, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=minRunFlag, value=0, createTime=1775720643827, updateTime=1775720643827, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166246539524, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN/file/pic, createTime=1775720643817, updateTime=1775720643817, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166280093961, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=silenceFlag, value=0, createTime=1775720643825, updateTime=1775720643825, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166233956611, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1775720643814, updateTime=1775720643814, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166259122438, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=themeColor, value=null, createTime=1775720643820, updateTime=1775720643820, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166267511047, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=themeStyle, value=null, createTime=1775720643822, updateTime=1775720643822, creator=18614031015, updator=18614031015)]), Website(id=1249025782681633001, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1249024232475115590, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN, language=EN, createTime=1775720552368, createBy=18614031015, updateTime=1775720607118, updateBy=18614031015, name=中国图象图形学报-英文, tplId=1146101810881728533, title=Journal of Image and Graphics, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1249026195371786511, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=articleTextType, value=kx, createTime=1775720650761, updateTime=1775720650761, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195355009292, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=banner, value=null, createTime=1775720650757, updateTime=1775720650757, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195392758034, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=grayFlag, value=0, createTime=1775720650766, updateTime=1775720650766, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195342426379, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=logo, value=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN/file/pic?fileId=TDRjKTHfgAnvFKZaDA70wA==, createTime=1775720650754, updateTime=1775720650754, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195409535252, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=minRunFlag, value=0, createTime=1775720650770, updateTime=1775720650770, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195367592206, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN/file/pic, createTime=1775720650760, updateTime=1775720650760, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195401146643, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=silenceFlag, value=0, createTime=1775720650768, updateTime=1775720650768, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195359203597, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1775720650758, updateTime=1775720650758, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195380175120, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=themeColor, value=null, createTime=1775720650763, updateTime=1775720650763, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195388563729, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=themeStyle, value=null, createTime=1775720650765, updateTime=1775720650765, creator=18614031015, updator=18614031015)])], journalTitle=中国图象图形学报, weixinUrl=null, journalUrl=https://www.cjig.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Image and Graphics, journalPhotoCn=uirXtX858YS3zEpFXZttJA==, journalPhotoEn=bud7qaxfvWHeFsbyBTAiKQ==, journalFirstLetter=Z, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN/10.11834/jig.250519, detailUrlEn=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN/10.11834/jig.250519, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN/PDF/10.11834/jig.250519, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN/PDF/10.11834/jig.250519, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1786809600000, fullTextJson=null, articleText=null, reference=null)
全屏
文章导航
PDF下载
11
5
关闭全屏
北京市海淀区学院南路86号
010-62662699（运营及技术支持）
qkjq@cast.org.cn
