Journal
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
Volume -, Issue -, Pages 15915-15924Publisher
IEEE COMPUTER SOC
DOI: 10.1109/CVPR46437.2021.01566
Keywords
-
Funding
- EPSRC [EP/M013774/1]
- Royal Society Research Professorship
- ERC [638009-IDIU]
- EPSRC [EP/M013774/1] Funding Source: UKRI
Ask authors/readers for more resources
This approach introduces a spatial attention mechanism and distinctiveness score to significantly improve performance when dealing with image pairs under large changes in viewpoint and context. Models using this approach achieve state of the art or competitive results in tasks such as local matching, camera localization, 3D reconstruction, and image stylization.
We propose a new approach to determine correspondences between image pairs in the wild under large changes in illumination, viewpoint, context, and material. While other approaches find correspondences between pairs of images by treating the images independently, we instead condition on both images to implicitly take account of the differences between them. To achieve this, we introduce (i) a spatial attention mechanism (a co-attention module, CoAM) for conditioning the learned features on both images, and (ii) a distinctiveness score used to choose the best matches at test time. CoAM can be added to standard architectures and trained using self-supervision or supervised data, and achieves a significant performance improvement under hard conditions, e.g. large viewpoint changes. We demonstrate that models using CoAM achieve state of the art or competitive results on a wide range of tasks: local matching, camera localization, 3D reconstruction, and image stylization.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available