CorrAdaptor: Adaptive Local Context Learning for Correspondence Pruning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929460398260224 |
|---|---|
| author | Zhu, Wei Liu, Yicheng He, Yuping Liao, Tangfei Zheng, Kang Xu, Xiaoqiu Wang, Tao Lu, Tong |
| author_facet | Zhu, Wei Liu, Yicheng He, Yuping Liao, Tangfei Zheng, Kang Xu, Xiaoqiu Wang, Tao Lu, Tong |
| contents | In the fields of computer vision and robotics, accurate pixel-level correspondences are essential for enabling advanced tasks such as structure-from-motion and simultaneous localization and mapping. Recent correspondence pruning methods usually focus on learning local consistency through k-nearest neighbors, which makes it difficult to capture robust context for each correspondence. We propose CorrAdaptor, a novel architecture that introduces a dual-branch structure capable of adaptively adjusting local contexts through both explicit and implicit local graph learning. Specifically, the explicit branch uses KNN-based graphs tailored for initial neighborhood identification, while the implicit branch leverages a learnable matrix to softly assign neighbors and adaptively expand the local context scope, significantly enhancing the model's robustness and adaptability to complex image variations. Moreover, we design a motion injection module to integrate motion consistency into the network to suppress the impact of outliers and refine local context learning, resulting in substantial performance improvements. The experimental results on extensive correspondence-based tasks indicate that our CorrAdaptor achieves state-of-the-art performance both qualitatively and quantitatively. The code and pre-trained models are available at https://github.com/TaoWangzj/CorrAdaptor. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_08134 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CorrAdaptor: Adaptive Local Context Learning for Correspondence Pruning Zhu, Wei Liu, Yicheng He, Yuping Liao, Tangfei Zheng, Kang Xu, Xiaoqiu Wang, Tao Lu, Tong Computer Vision and Pattern Recognition In the fields of computer vision and robotics, accurate pixel-level correspondences are essential for enabling advanced tasks such as structure-from-motion and simultaneous localization and mapping. Recent correspondence pruning methods usually focus on learning local consistency through k-nearest neighbors, which makes it difficult to capture robust context for each correspondence. We propose CorrAdaptor, a novel architecture that introduces a dual-branch structure capable of adaptively adjusting local contexts through both explicit and implicit local graph learning. Specifically, the explicit branch uses KNN-based graphs tailored for initial neighborhood identification, while the implicit branch leverages a learnable matrix to softly assign neighbors and adaptively expand the local context scope, significantly enhancing the model's robustness and adaptability to complex image variations. Moreover, we design a motion injection module to integrate motion consistency into the network to suppress the impact of outliers and refine local context learning, resulting in substantial performance improvements. The experimental results on extensive correspondence-based tasks indicate that our CorrAdaptor achieves state-of-the-art performance both qualitatively and quantitatively. The code and pre-trained models are available at https://github.com/TaoWangzj/CorrAdaptor. |
| title | CorrAdaptor: Adaptive Local Context Learning for Correspondence Pruning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.08134 |