Implicit Field Supervision For Robust Non-Rigid Shape Matching - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Implicit Field Supervision For Robust Non-Rigid Shape Matching

Résumé

Establishing a correspondence between two non-rigidly deforming shapes is one of the most fundamental problems in visual computing. Existing methods often show weak resilience when presented with challenges innate to real-world data such as noise, outliers, self-occlusion etc. On the other hand, auto-decoders have demonstrated strong expressive power in learning geometrically meaningful latent embeddings. However, their use in shape analysis has been limited. In this paper, we introduce an approach based on an auto-decoder framework, that learns a continuous shape-wise deformation field over a fixed template. By supervising the deformation field for points on-surface and regularizing for points off-surface through a novel Signed Distance Regularization (SDR), we learn an alignment between the template and shape volumes. Trained on clean watertight meshes, without any data-augmentation, we demonstrate compelling performance on compromised data and realworld scans.
Fichier principal
Vignette du fichier
2203.07694.pdf (8 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03912307 , version 1 (23-12-2022)

Identifiants

  • HAL Id : hal-03912307 , version 1

Citer

Ramana Sundararaman, Gautam Pai, Maks Ovsjanikov. Implicit Field Supervision For Robust Non-Rigid Shape Matching. ECCV 2022 - European Conference on Computer Vision, Oct 2022, Tel Aviv, Israel. ⟨hal-03912307⟩
6 Consultations
36 Téléchargements

Partager

Gmail Facebook X LinkedIn More