收藏切换
Neural radiation field reconstruction based on feature point-guided interference identification
收藏切换
PDF
Hao REN, Shaobo LI, Mao GONG, Bo WANG
Journal of Graphics | 2026, 47(1) : 111 - 119
Less
收藏切换
Journal of Graphics | 2026, 47(1): 111-119
Image Processing and Computer Vision
Neural radiation field reconstruction based on feature point-guided interference identification
Full
Hao REN, Shaobo LI, Mao GONG, Bo WANG
Affiliations
  • School of Automation and Electrical Engineering, Inner Mongolia University of Science and Technology, Baotou Inner Mongolia 014010, China
Published: 2026-02-28 doi: 10.11996/JG.j.2095-302X.2026010111
Outline
收藏切换

To address the challenge of achieving high-quality 3D reconstruction with Neural Radiation Fields (NeRF) under the influence of occluding objects, a method based on the collaborative optimization of Structure-from-Motion (SfM) and the Segment Anything Model (SAM) was propose. Building upon the Scale-Invariant Feature Transform (SIFT) algorithm within the SfM reconstruction process, geometric inconsistencies in dynamic scenes were leveraged for feature point identification and matching. Unmatched feature points were treated as dynamic occluders, guiding the SAM model—capable of point-guided segmentation—to perform dynamic occluder segmentation and generate a static scene mask. Based on the segmentation results, mask-aware volumetric rendering was used to predict colors and a quadruple loss function was established: comprising reconstruction loss, structural consistency loss, adversarial loss, and self-supervised patching loss. These objectives were jointly optimized to constrain the color output in patched regions. After iterative training, consistent restoration of geometric structure and appearance in occluded areas across multiple viewpoints was achieved. The radiometric integrity was preserved while occlusions were removed. Validation on public dynamic scene datasets demonstrated that the mask-based volumetric rendering combined with joint optimization produced an average Peak Signal-to-Noise Ratio (PSNR) improvement of 5.24 dB over baseline models and mainstream occlusion removal methods, alongside a 35% reduction in Learned Perceptual Image Patch Similarity (LPIPS). This approach established a new paradigm for 3D reconstruction in complex dynamic environments.

neural radiation field  /  3D reconstruction  /  dynamic scene  /  occlusion removal  /  computer vision
Hao REN, Shaobo LI, Mao GONG, Bo WANG. Neural radiation field reconstruction based on feature point-guided interference identification[J]. Journal of Graphics, 2026 , 47 (1) : 111 -119 . DOI: 10.11996/JG.j.2095-302X.2026010111
  • Inner Mongolia Natural Science Foundation(2022LHMS06002)
Year 2026 volume 47 Issue 1
PDF
10
3
Cite this Article
BibTeX
Article Info
doi: 10.11996/JG.j.2095-302X.2026010111
  • Receive Date:2025-05-30
  • Online Date:2026-05-19
  • Published:2026-02-28
Article Data
Affiliations
History
  • Received:2025-05-30
  • Accepted:2025-09-08
Funding
Inner Mongolia Natural Science Foundation(2022LHMS06002)
Affiliations
    School of Automation and Electrical Engineering, Inner Mongolia University of Science and Technology, Baotou Inner Mongolia 014010, China

Corresponding:

LI Shaobo,E-mail:
References
Share
https://castjournals.cast.org.cn/joweb/txxb/EN/10.11996/JG.j.2095-302X.2026010111
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT