Human-Centric Foundation Models: Perception, Generation and Agentic Modeling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tang, Shixiang, Wang, Yizhou, Chen, Lu, Wang, Yuan, Peng, Sida, Xu, Dan, Ouyang, Wanli
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916610543976448
author Tang, Shixiang
Wang, Yizhou
Chen, Lu
Wang, Yuan
Peng, Sida
Xu, Dan
Ouyang, Wanli
author_facet Tang, Shixiang
Wang, Yizhou
Chen, Lu
Wang, Yuan
Peng, Sida
Xu, Dan
Ouyang, Wanli
contents Human understanding and generation are critical for modeling digital humans and humanoid embodiments. Recently, Human-centric Foundation Models (HcFMs) inspired by the success of generalist models, such as large language and vision models, have emerged to unify diverse human-centric tasks into a single framework, surpassing traditional task-specific approaches. In this survey, we present a comprehensive overview of HcFMs by proposing a taxonomy that categorizes current approaches into four groups: (1) Human-centric Perception Foundation Models that capture fine-grained features for multi-modal 2D and 3D understanding. (2) Human-centric AIGC Foundation Models that generate high-fidelity, diverse human-related content. (3) Unified Perception and Generation Models that integrate these capabilities to enhance both human understanding and synthesis. (4) Human-centric Agentic Foundation Models that extend beyond perception and generation to learn human-like intelligence and interactive behaviors for humanoid embodied tasks. We review state-of-the-art techniques, discuss emerging challenges and future research directions. This survey aims to serve as a roadmap for researchers and practitioners working towards more robust, versatile, and intelligent digital human and embodiments modeling.
format Preprint
id arxiv_https___arxiv_org_abs_2502_08556
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Human-Centric Foundation Models: Perception, Generation and Agentic Modeling
Tang, Shixiang
Wang, Yizhou
Chen, Lu
Wang, Yuan
Peng, Sida
Xu, Dan
Ouyang, Wanli
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Multimedia
Human understanding and generation are critical for modeling digital humans and humanoid embodiments. Recently, Human-centric Foundation Models (HcFMs) inspired by the success of generalist models, such as large language and vision models, have emerged to unify diverse human-centric tasks into a single framework, surpassing traditional task-specific approaches. In this survey, we present a comprehensive overview of HcFMs by proposing a taxonomy that categorizes current approaches into four groups: (1) Human-centric Perception Foundation Models that capture fine-grained features for multi-modal 2D and 3D understanding. (2) Human-centric AIGC Foundation Models that generate high-fidelity, diverse human-related content. (3) Unified Perception and Generation Models that integrate these capabilities to enhance both human understanding and synthesis. (4) Human-centric Agentic Foundation Models that extend beyond perception and generation to learn human-like intelligence and interactive behaviors for humanoid embodied tasks. We review state-of-the-art techniques, discuss emerging challenges and future research directions. This survey aims to serve as a roadmap for researchers and practitioners working towards more robust, versatile, and intelligent digital human and embodiments modeling.
title Human-Centric Foundation Models: Perception, Generation and Agentic Modeling
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Multimedia
url https://arxiv.org/abs/2502.08556