CoMatcher: Multi-View Collaborative Feature Matching
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918127667773440 |
|---|---|
| author | Zhang, Jintao Xia, Zimin Dong, Mingyue Shen, Shuhan Yue, Linwei Zheng, Xianwei |
| author_facet | Zhang, Jintao Xia, Zimin Dong, Mingyue Shen, Shuhan Yue, Linwei Zheng, Xianwei |
| contents | This paper proposes a multi-view collaborative matching strategy for reliable track construction in complex scenarios. We observe that the pairwise matching paradigms applied to image set matching often result in ambiguous estimation when the selected independent pairs exhibit significant occlusions or extreme viewpoint changes. This challenge primarily stems from the inherent uncertainty in interpreting intricate 3D structures based on limited two-view observations, as the 3D-to-2D projection leads to significant information loss. To address this, we introduce CoMatcher, a deep multi-view matcher to (i) leverage complementary context cues from different views to form a holistic 3D scene understanding and (ii) utilize cross-view projection consistency to infer a reliable global solution. Building on CoMatcher, we develop a groupwise framework that fully exploits cross-view relationships for large-scale matching tasks. Extensive experiments on various complex scenarios demonstrate the superiority of our method over the mainstream two-view matching paradigm. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_01872 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CoMatcher: Multi-View Collaborative Feature Matching Zhang, Jintao Xia, Zimin Dong, Mingyue Shen, Shuhan Yue, Linwei Zheng, Xianwei Computer Vision and Pattern Recognition I.4.8; I.2.10; I.5.4 This paper proposes a multi-view collaborative matching strategy for reliable track construction in complex scenarios. We observe that the pairwise matching paradigms applied to image set matching often result in ambiguous estimation when the selected independent pairs exhibit significant occlusions or extreme viewpoint changes. This challenge primarily stems from the inherent uncertainty in interpreting intricate 3D structures based on limited two-view observations, as the 3D-to-2D projection leads to significant information loss. To address this, we introduce CoMatcher, a deep multi-view matcher to (i) leverage complementary context cues from different views to form a holistic 3D scene understanding and (ii) utilize cross-view projection consistency to infer a reliable global solution. Building on CoMatcher, we develop a groupwise framework that fully exploits cross-view relationships for large-scale matching tasks. Extensive experiments on various complex scenarios demonstrate the superiority of our method over the mainstream two-view matching paradigm. |
| title | CoMatcher: Multi-View Collaborative Feature Matching |
| topic | Computer Vision and Pattern Recognition I.4.8; I.2.10; I.5.4 |
| url | https://arxiv.org/abs/2504.01872 |