SRFeat: Learning Locally Accurate and Globally Consistent Non-Rigid Shape Correspondence
| Autor: | Lei Li, Souhaib Attaiki, Maks Ovsjanikov |
|---|---|
| Přispěvatelé: | La Géometrie au Service du Numérique (GEOMERIX), Laboratoire d'informatique de l'École polytechnique [Palaiseau] (LIX), École polytechnique (X)-Centre National de la Recherche Scientifique (CNRS)-École polytechnique (X)-Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Institut Polytechnique de Paris (IP Paris), ANR-20-CHIA-0019,AIGRETTE,Analyse des Collections des Données Géométriques de Grande Taille(2020), European Project: 758800,ERC,ERC-2017-StG-758800,EXPROTEA(2018) |
| Jazyk: | angličtina |
| Rok vydání: | 2022 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Graphics Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] Graphics (cs.GR) [INFO.INFO-GR]Computer Science [cs]/Graphics [cs.GR] |
| Zdroj: | 3DV 2022-International Conference on 3D Vision 3DV 2022-International Conference on 3D Vision, Sep 2022, Prague / Hybrid, Czech Republic |
| Popis: | In this work, we present a novel learning-based framework that combines the local accuracy of contrastive learning with the global consistency of geometric approaches, for robust non-rigid matching. We first observe that while contrastive learning can lead to powerful point-wise features, the learned correspondences commonly lack smoothness and consistency, owing to the purely combinatorial nature of the standard contrastive losses. To overcome this limitation we propose to boost contrastive feature learning with two types of smoothness regularization that inject geometric information into correspondence learning. With this novel combination in hand, the resulting features are both highly discriminative across individual points, and, at the same time, lead to robust and consistent correspondences, through simple proximity queries. Our framework is general and is applicable to local feature learning in both the 3D and 2D domains. We demonstrate the superiority of our approach through extensive experiments on a wide range of challenging matching benchmarks, including 3D non-rigid shape correspondence and 2D image keypoint matching. Comment: 3DV 2022. Code and data: https://github.com/craigleili/SRFeat |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|