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

Zerui Chen
Shizhe Chen
Cordelia Schmid
Ivan Laptev
Inria, École normale supérieure, CNRS, PSL Research University
Published at CVPR, 2023


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.


Our method. The overview of our proposed single-frame model. Our method reconstructs realistic hand and object meshes from a single RGB image. Marching Cubes algorithm is used at test time to extract meshes.


author       = {Chen, Zerui and Chen, Shizhe and Schmid, Cordelia and Laptev, Ivan},
title        = {{gSDF}: {Geometry-Driven} Signed Distance Functions for {3D} Hand-Object Reconstruction},
booktitle    = {CVPR},
year         = {2023},


This work was granted access to the HPC resources of IDRIS under the allocation AD011013147 made by GENCI. It was funded in part by the French government under management of Agence Nationale de la Recherche as part of the “Investissements d’avenir” program, reference ANR19-P3IA-0001 (PRAIRIE 3IA Institute) and by Louis Vuitton ENS Chair on Artificial Intelligence.