Learning Rotation-Equivariant Features for Visual Correspondence
- Title
- Learning Rotation-Equivariant Features for Visual Correspondence
- Authors
- JONGMIN, LEE; KIM, BYUNGJIN; KIM, SEUNG WOOK; CHO, MINSU
- Date Issued
- 2023-06
- Publisher
- IEEE Computer Society
- Abstract
- Extracting discriminative local features that are invariant to imaging variations is an integral part of establishing correspondences between images. In this work, we introduce a self-supervised learning framework to extract discriminative rotation-invariant descriptors using group-equivariant CNNs. Thanks to employing group-equivariant CNNs, our method effectively learns to obtain rotation-equivariant features and their orientations explicitly, without having to perform sophisticated data augmentations. The resultant features and their orientations are further processed by group aligning, a novel invariant mapping technique that shifts the group-equivariant features by their orientations along the group dimension. Our group aligning technique achieves rotation-invariance without any collapse of the group dimension and thus eschews loss of discriminability. The proposed method is trained end-to-end in a self-supervised manner, where we use an orientation alignment loss for the orientation estimation and a contrastive descriptor loss for robust local descriptors to geometric/photometric variations. Our method demonstrates state-of-the-art matching accuracy among existing rotation-invariant descriptors under varying rotation and also shows competitive results when transferred to the task of keypoint matching and camera pose estimation.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/121034
- Article Type
- Conference
- Citation
- 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, page. 21887 - 21897, 2023-06
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.