Learning Accurate Template Matching with Differentiable Coarse-to-Fine Correspondence Refinement
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910570584735744 |
|---|---|
| author | Gao, Zhirui Yi, Renjiao Qin, Zheng Ye, Yunfan Zhu, Chenyang Xu, Kai |
| author_facet | Gao, Zhirui Yi, Renjiao Qin, Zheng Ye, Yunfan Zhu, Chenyang Xu, Kai |
| contents | Template matching is a fundamental task in computer vision and has been studied for decades. It plays an essential role in manufacturing industry for estimating the poses of different parts, facilitating downstream tasks such as robotic grasping. Existing methods fail when the template and source images have different modalities, cluttered backgrounds or weak textures. They also rarely consider geometric transformations via homographies, which commonly exist even for planar industrial parts. To tackle the challenges, we propose an accurate template matching method based on differentiable coarse-to-fine correspondence refinement. We use an edge-aware module to overcome the domain gap between the mask template and the grayscale image, allowing robust matching. An initial warp is estimated using coarse correspondences based on novel structure-aware information provided by transformers. This initial alignment is passed to a refinement network using references and aligned images to obtain sub-pixel level correspondences which are used to give the final geometric transformation. Extensive evaluation shows that our method is significantly better than state-of-the-art methods and baselines, providing good generalization ability and visually plausible results even on unseen real data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_08438 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Learning Accurate Template Matching with Differentiable Coarse-to-Fine Correspondence Refinement Gao, Zhirui Yi, Renjiao Qin, Zheng Ye, Yunfan Zhu, Chenyang Xu, Kai Computer Vision and Pattern Recognition Template matching is a fundamental task in computer vision and has been studied for decades. It plays an essential role in manufacturing industry for estimating the poses of different parts, facilitating downstream tasks such as robotic grasping. Existing methods fail when the template and source images have different modalities, cluttered backgrounds or weak textures. They also rarely consider geometric transformations via homographies, which commonly exist even for planar industrial parts. To tackle the challenges, we propose an accurate template matching method based on differentiable coarse-to-fine correspondence refinement. We use an edge-aware module to overcome the domain gap between the mask template and the grayscale image, allowing robust matching. An initial warp is estimated using coarse correspondences based on novel structure-aware information provided by transformers. This initial alignment is passed to a refinement network using references and aligned images to obtain sub-pixel level correspondences which are used to give the final geometric transformation. Extensive evaluation shows that our method is significantly better than state-of-the-art methods and baselines, providing good generalization ability and visually plausible results even on unseen real data. |
| title | Learning Accurate Template Matching with Differentiable Coarse-to-Fine Correspondence Refinement |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2303.08438 |