Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Youliang, Li, Ronghui, Zhang, Yachao, Pan, Liang, Wang, Jingbo, Liu, Yebin, Li, Xiu
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2412.17377
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912166707200000
author Zhang, Youliang
Li, Ronghui
Zhang, Yachao
Pan, Liang
Wang, Jingbo
Liu, Yebin
Li, Xiu
author_facet Zhang, Youliang
Li, Ronghui
Zhang, Yachao
Pan, Liang
Wang, Jingbo
Liu, Yebin
Li, Xiu
contents Extracting physically plausible 3D human motion from videos is a critical task. Although existing simulation-based motion imitation methods can enhance the physical quality of daily motions estimated from monocular video capture, extending this capability to high-difficulty motions remains an open challenge. This can be attributed to some flawed motion clips in video-based motion capture results and the inherent complexity in modeling high-difficulty motions. Therefore, sensing the advantage of segmentation in localizing human body, we introduce a mask-based motion correction module (MCM) that leverages motion context and video mask to repair flawed motions, producing imitation-friendly motions; and propose a physics-based motion transfer module (PTM), which employs a pretrain and adapt approach for motion imitation, improving physical plausibility with the ability to handle in-the-wild and challenging motions. Our approach is designed as a plug-and-play module to physically refine the video motion capture results, including high-difficulty in-the-wild motions. Finally, to validate our approach, we collected a challenging in-the-wild test set to establish a benchmark, and our method has demonstrated effectiveness on both the new benchmark and existing public datasets.https://physicalmotionrestoration.github.io
format Preprint
id arxiv_https___arxiv_org_abs_2412_17377
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Plug-and-Play Physical Motion Restoration Approach for In-the-Wild High-Difficulty Motions
Zhang, Youliang
Li, Ronghui
Zhang, Yachao
Pan, Liang
Wang, Jingbo
Liu, Yebin
Li, Xiu
Computer Vision and Pattern Recognition
Artificial Intelligence
Extracting physically plausible 3D human motion from videos is a critical task. Although existing simulation-based motion imitation methods can enhance the physical quality of daily motions estimated from monocular video capture, extending this capability to high-difficulty motions remains an open challenge. This can be attributed to some flawed motion clips in video-based motion capture results and the inherent complexity in modeling high-difficulty motions. Therefore, sensing the advantage of segmentation in localizing human body, we introduce a mask-based motion correction module (MCM) that leverages motion context and video mask to repair flawed motions, producing imitation-friendly motions; and propose a physics-based motion transfer module (PTM), which employs a pretrain and adapt approach for motion imitation, improving physical plausibility with the ability to handle in-the-wild and challenging motions. Our approach is designed as a plug-and-play module to physically refine the video motion capture results, including high-difficulty in-the-wild motions. Finally, to validate our approach, we collected a challenging in-the-wild test set to establish a benchmark, and our method has demonstrated effectiveness on both the new benchmark and existing public datasets.https://physicalmotionrestoration.github.io
title A Plug-and-Play Physical Motion Restoration Approach for In-the-Wild High-Difficulty Motions
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2412.17377