Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Mengyuan, Wang, Xinshun, Fang, Zhongbin, Ye, Deheng, Li, Xia, Tang, Tao, Wu, Songtao, Li, Xiangtai, Yang, Ming-Hsuan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911105695088640
author Liu, Mengyuan
Wang, Xinshun
Fang, Zhongbin
Ye, Deheng
Li, Xia
Tang, Tao
Wu, Songtao
Li, Xiangtai
Yang, Ming-Hsuan
author_facet Liu, Mengyuan
Wang, Xinshun
Fang, Zhongbin
Ye, Deheng
Li, Xia
Tang, Tao
Wu, Songtao
Li, Xiangtai
Yang, Ming-Hsuan
contents This paper aims to model 3D human motion across domains, where a single model is expected to handle multiple modalities, tasks, and datasets. Existing cross-domain models often rely on domain-specific components and multi-stage training, which limits their practicality and scalability. To overcome these challenges, we propose a new setting to train a unified cross-domain model through a single process, eliminating the need for domain-specific components and multi-stage training. We first introduce Pose-in-Context (PiC), which leverages in-context learning to create a pose-centric cross-domain model. While PiC generalizes across multiple pose-based tasks and datasets, it encounters difficulties with modality diversity, prompting strategy, and contextual dependency handling. We thus propose Human-in-Context (HiC), an extension of PiC that broadens generalization across modalities, tasks, and datasets. HiC combines pose and mesh representations within a unified framework, expands task coverage, and incorporates larger-scale datasets. Additionally, HiC introduces a max-min similarity prompt sampling strategy to enhance generalization across diverse domains and a network architecture with dual-branch context injection for improved handling of contextual dependencies. Extensive experimental results show that HiC performs better than PiC in terms of generalization, data scale, and performance across a wide range of domains. These results demonstrate the potential of HiC for building a unified cross-domain 3D human motion model with improved flexibility and scalability. The source codes and models are available at https://github.com/BradleyWang0416/Human-in-Context.
format Preprint
id arxiv_https___arxiv_org_abs_2508_10897
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning
Liu, Mengyuan
Wang, Xinshun
Fang, Zhongbin
Ye, Deheng
Li, Xia
Tang, Tao
Wu, Songtao
Li, Xiangtai
Yang, Ming-Hsuan
Computer Vision and Pattern Recognition
This paper aims to model 3D human motion across domains, where a single model is expected to handle multiple modalities, tasks, and datasets. Existing cross-domain models often rely on domain-specific components and multi-stage training, which limits their practicality and scalability. To overcome these challenges, we propose a new setting to train a unified cross-domain model through a single process, eliminating the need for domain-specific components and multi-stage training. We first introduce Pose-in-Context (PiC), which leverages in-context learning to create a pose-centric cross-domain model. While PiC generalizes across multiple pose-based tasks and datasets, it encounters difficulties with modality diversity, prompting strategy, and contextual dependency handling. We thus propose Human-in-Context (HiC), an extension of PiC that broadens generalization across modalities, tasks, and datasets. HiC combines pose and mesh representations within a unified framework, expands task coverage, and incorporates larger-scale datasets. Additionally, HiC introduces a max-min similarity prompt sampling strategy to enhance generalization across diverse domains and a network architecture with dual-branch context injection for improved handling of contextual dependencies. Extensive experimental results show that HiC performs better than PiC in terms of generalization, data scale, and performance across a wide range of domains. These results demonstrate the potential of HiC for building a unified cross-domain 3D human motion model with improved flexibility and scalability. The source codes and models are available at https://github.com/BradleyWang0416/Human-in-Context.
title Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.10897