gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstruction - PaRis AI Research InstitutE Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstruction

Résumé

Signed distance functions (SDFs) is an attractive framework that has recently shown promising results for 3D shape reconstruction from images. SDFs seamlessly generalize to different shape resolutions and topologies but lack explicit modelling of the underlying 3D geometry. In this work, we exploit the hand structure and use it as guidance for SDF-based shape reconstruction. In particular, we address reconstruction of hands and manipulated objects from monocular RGB images. To this end, we estimate poses of hands and objects and use them to guide 3D reconstruction. More specifically, we predict kinematic chains of pose transformations and align SDFs with highly-articulated hand poses. We improve the visual features of 3D points with geometry alignment and further leverage temporal information to enhance the robustness to occlusion and motion blurs. We conduct extensive experiments on the challenging ObMan and DexYCB benchmarks and demonstrate significant improvements of the proposed method over the state of the art.
Fichier principal
Vignette du fichier
gSDF_arxiv.pdf (9.2 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04095352 , version 1 (11-05-2023)

Identifiants

Citer

Zerui Chen, Shizhe Chen, Cordelia Schmid, Ivan Laptev. gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstruction. CVPR 2023 - IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023, Jun 2023, Vancouver (Canada), Canada. ⟨hal-04095352⟩
45 Consultations
7 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More