Title | ||
---|---|---|
PUMP: Pyramidal and Uniqueness Matching Priors for Unsupervised Learning of Local Descriptors |
Abstract | ||
---|---|---|
Existing approaches for learning local image descriptors have shown remarkable achievements in a wide range of geometric tasks. However, most of them require perpixel correspondence-level supervision, which is difficult to acquire at scale and in high quality. In this paper, we propose to explicitly integrate two matching priors in a single loss in order to learn local descriptors without supervision. Given two images depicting the same scene, we extract pixel descriptors and build a correlation volume. The first prior enforces the local consistency of matches in this volume via a pyramidal structure iteratively constructed using a non-parametric module. The second prior exploits the fact that each descriptor should match with at most one descriptor from the other image. We combine our unsupervised loss with a standard self-supervised loss trained from synthetic image augmentations. Feature descriptors learned by the proposed approach outperform their fully- and self-supervised counterparts on various geometric benchmarks such as visual localization and image matching, achieving state-of-the-art performance. Project webpage: https://europe.naverlabs.com/research/3d-vision/pump. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/CVPR52688.2022.00390 | IEEE Conference on Computer Vision and Pattern Recognition |
Keywords | DocType | Volume |
3D from single images, Pose estimation and tracking, Self-& semi-& meta- & unsupervised learning | Conference | 2022 |
Issue | Citations | PageRank |
1 | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jerome Revaud | 1 | 0 | 0.68 |
Vincent Leroy | 2 | 0 | 0.34 |
Philippe Weinzaepfel | 3 | 378 | 19.38 |
Boris Chidlovskii | 4 | 0 | 0.34 |