收藏切换
An image matching method for large viewpoint variation scenarios
收藏切换
PDF
Mengli XIANG, Zhiyong HUANG, Yali SHE, Tuojun DING
Journal of Graphics | 2026, 47(1) : 90 - 98
Less
收藏切换
Journal of Graphics | 2026, 47(1): 90-98
Image Processing and Computer Vision
An image matching method for large viewpoint variation scenarios
Full
Mengli XIANG, Zhiyong HUANG, Yali SHE, Tuojun DING
Affiliations
  • College of Computer and Information Technology, China Three Gorges University, Yichang Hubei 443000, China
Published: 2026-02-28 doi: 10.11996/JG.j.2095-302X.2026010090
Outline
收藏切换

To address the significant decline in matching accuracy and the number of correspondences exhibited by existing image-matching methods under large viewpoint variations, an improved image-matching approach based on E-LoFTR was proposed. Firstly, based on a strategy of viewpoint rectification followed by fine-grained matching, a novel two-stage SIFT-based viewpoint-rectification module was proposed, which leveraged the viewpoint invariance of the Scale-Invariant Feature Transform (SIFT) algorithm and the geometric alignment capability of homography to enhance matching accuracy under large viewpoint variations. Then, a directional-gated attention mechanism was designed that employed a cascaded structure of multi-directional convolutions and dynamic gating to extract queries (Q), keys (K), and values (V). The injected geometric priors significantly enhanced the model’s robustness. Lastly, to mitigate information loss during the upsampling of fused features, the Fusion-DySample module was incorporated to further improve performance. Experimental results on the public MegaDepth dataset showed that our method achieved relative pose estimation AUCs of 57.1%, 72.7%, and 83.9% under rotation error thresholds of 5°, 10°, and 20°, respectively, outperforming E-LoFTR by 0.7%, 0.5%, and 0.4%. On the newly constructed NewMega dataset based on MegaDepth and on a private industrial dataset, our method also demonstrated substantial improvements in both the number of matches and matching accuracy.

image matching  /  E-LoFTR  /  large perspective variation  /  SIFT  /  attention mechanism
Mengli XIANG, Zhiyong HUANG, Yali SHE, Tuojun DING. An image matching method for large viewpoint variation scenarios[J]. Journal of Graphics, 2026 , 47 (1) : 90 -98 . DOI: 10.11996/JG.j.2095-302X.2026010090
  • National Natural Science Foundation of China(62371271)
Year 2026 volume 47 Issue 1
PDF
3
1
Cite this Article
BibTeX
Article Info
doi: 10.11996/JG.j.2095-302X.2026010090
  • Receive Date:2025-06-24
  • Online Date:2026-05-19
  • Published:2026-02-28
Article Data
Affiliations
History
  • Received:2025-06-24
  • Accepted:2025-08-27
Funding
National Natural Science Foundation of China(62371271)
Affiliations
    College of Computer and Information Technology, China Three Gorges University, Yichang Hubei 443000, China

Corresponding:

HUANG Zhiyong,E-mail:
References
Share
https://castjournals.cast.org.cn/joweb/txxb/EN/10.11996/JG.j.2095-302X.2026010090
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