Saved in:
Bibliographic Details
Main Authors: Luo, Haowen, Liu, Yunze, Yi, Li
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.11481
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914802428805120
author Luo, Haowen
Liu, Yunze
Yi, Li
author_facet Luo, Haowen
Liu, Yunze
Yi, Li
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_11481
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Physics-aware Hand-object Interaction Denoising
Luo, Haowen
Liu, Yunze
Yi, Li
Computer Vision and Pattern Recognition
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.
title Physics-aware Hand-object Interaction Denoising
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.11481