Physics-Aware Hand-Object Interaction Denoising
Authors:
- 16 June 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2341-2350
Abstract
The credibility and practicality of a reconstructed hand-object interaction sequence depend largely on its physical plausibility. However, due to high occlusions during hand-object interaction, physical plausibility remains a challenging criterion for purely vision-based tracking methods. To address this issue and enhance the results of existing hand trackers, this paper proposes a novel physically-aware hand motion de-noising method. Specifically, we introduce two learned loss terms that explicitly capture two crucial aspects of physical plausibility: grasp credibility and manipulation feasibility. These terms are used to train a physically-aware de-noising network. Qualitative and quantitative experiments demonstrate that our approach significantly improves both fine-grained physical plausibility and overall pose accuracy, surpassing current state-of-the-art de-noising methods.Keywords
All Related Versions
This publication has 30 references indexed in Scilit:
- TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement2022
- Towards Unconstrained Joint Hand-Object Reconstruction From RGB Videos2021
- ContactPose: A Dataset of Grasps with Object Contact and Hand Pose2020
- GRAB: A Dataset of Whole-Body Human Grasping of Objects2020
- Leveraging Photometric Consistency Over Time for Sparsely Supervised Hand-Object Reconstruction2020
- ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imaging2019
- 3D Hand Shape and Pose Estimation From a Single RGB Image2019
- 3D Hand Shape and Pose From Images in the Wild2019
- Real-Time Hand Tracking Using a Sum of Anisotropic Gaussians Model2014
- Physically Plausible 3D Scene Tracking: The Single Actor Hypothesis2013