SAM-Body4D: Training-Free 4D Human Body Mesh Recovery from Videos

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Gao, Mingqi, Miao, Yunqi, Han, Jungong
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909951092326400
author Gao, Mingqi
Miao, Yunqi
Han, Jungong
author_facet Gao, Mingqi
Miao, Yunqi
Han, Jungong
contents Human Mesh Recovery (HMR) aims to reconstruct 3D human pose and shape from 2D observations and is fundamental to human-centric understanding in real-world scenarios. While recent image-based HMR methods such as SAM 3D Body achieve strong robustness on in-the-wild images, they rely on per-frame inference when applied to videos, leading to temporal inconsistency and degraded performance under occlusions. We address these issues without extra training by leveraging the inherent human continuity in videos. We propose SAM-Body4D, a training-free framework for temporally consistent and occlusion-robust HMR from videos. We first generate identity-consistent masklets using a promptable video segmentation model, then refine them with an Occlusion-Aware module to recover missing regions. The refined masklets guide SAM 3D Body to produce consistent full-body mesh trajectories, while a padding-based parallel strategy enables efficient multi-human inference. Experimental results demonstrate that SAM-Body4D achieves improved temporal stability and robustness in challenging in-the-wild videos, without any retraining. Our code and demo are available at: https://github.com/gaomingqi/sam-body4d.
format Preprint
id arxiv_https___arxiv_org_abs_2512_08406
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SAM-Body4D: Training-Free 4D Human Body Mesh Recovery from Videos
Gao, Mingqi
Miao, Yunqi
Han, Jungong
Computer Vision and Pattern Recognition
Human Mesh Recovery (HMR) aims to reconstruct 3D human pose and shape from 2D observations and is fundamental to human-centric understanding in real-world scenarios. While recent image-based HMR methods such as SAM 3D Body achieve strong robustness on in-the-wild images, they rely on per-frame inference when applied to videos, leading to temporal inconsistency and degraded performance under occlusions. We address these issues without extra training by leveraging the inherent human continuity in videos. We propose SAM-Body4D, a training-free framework for temporally consistent and occlusion-robust HMR from videos. We first generate identity-consistent masklets using a promptable video segmentation model, then refine them with an Occlusion-Aware module to recover missing regions. The refined masklets guide SAM 3D Body to produce consistent full-body mesh trajectories, while a padding-based parallel strategy enables efficient multi-human inference. Experimental results demonstrate that SAM-Body4D achieves improved temporal stability and robustness in challenging in-the-wild videos, without any retraining. Our code and demo are available at: https://github.com/gaomingqi/sam-body4d.
title SAM-Body4D: Training-Free 4D Human Body Mesh Recovery from Videos
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.08406