Towards unconstrained joint hand-object reconstruction from RGB videos - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Towards unconstrained joint hand-object reconstruction from RGB videos

Abstract

Our work aims to obtain 3D reconstruction of hands and manipulated objects from monocular videos. Reconstructing hand-object manipulations holds a great potential for robotics and learning from human demonstrations. The supervised learning approach to this problem, however, requires 3D supervision and remains limited to constrained laboratory settings and simulators for which 3D ground truth is available. In this paper we first propose a learning-free fitting approach for hand-object reconstruction which can seamlessly handle two-hand object interactions. Our method relies on cues obtained with common methods for object detection, hand pose estimation and instance segmentation. We quantitatively evaluate our approach and show that it can be applied to datasets with varying levels of difficulty for which training data is unavailable.
Fichier principal
Vignette du fichier
3dv_hand_object (3).pdf (2.86 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03615879 , version 1 (23-03-2022)

Identifiers

Cite

Yana Hasson, Gül Varol, Cordelia Schmid, Ivan Laptev. Towards unconstrained joint hand-object reconstruction from RGB videos. 3DV 2021 - International Conference on 3D Vision, Dec 2021, London, United Kingdom. ⟨hal-03615879⟩
84 View
106 Download

Altmetric

Share

Gmail Facebook X LinkedIn More