AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstruction - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstruction

Résumé

Recent work achieved impressive progress towards joint reconstruction of hands and manipulated objects from monocular color images. Existing methods focus on two alternative representations in terms of either parametric meshes or signed distance fields (SDFs). On one side, parametric models can benefit from prior knowledge at the cost of limited shape deformations and mesh resolutions. Mesh models, hence, may fail to precisely reconstruct details such as contact surfaces of hands and objects. SDF-based methods, on the other side, can represent arbitrary details but are lacking explicit priors. In this work we aim to improve SDF models using priors provided by parametric representations. In particular, we propose a joint learning framework that disentangles the pose and the shape. We obtain hand and object poses from parametric models and use them to align SDFs in 3D space. We show that such aligned SDFs better focus on reconstructing shape details and improve reconstruction accuracy both for hands and objects. We evaluate our method and demonstrate significant improvements over the state of the art on the challenging ObMan and DexYCB benchmarks.
Fichier principal
Vignette du fichier
AlignSDF_hal.pdf (11.75 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03761124 , version 1 (25-08-2022)

Identifiants

Citer

Zerui Chen, Yana Hasson, Cordelia Schmid, Ivan Laptev. AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstruction. ECCV 2022 - European Conference on Computer Vision, Oct 2022, Tel Aviv-Jaffa, Israel. ⟨hal-03761124⟩
130 Consultations
39 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More