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

TL;DR

This survey reviews the development of Human-centric Foundation Models (HcFMs) that unify perception, generation, and agentic capabilities for modeling digital humans and humanoid embodiments, highlighting recent advances and future challenges.

Contribution

It provides a comprehensive taxonomy and overview of HcFMs, categorizing approaches into perception, generation, unified models, and agentic models, serving as a roadmap for future research.

Findings

HcFMs unify diverse human-centric tasks into a single framework.

State-of-the-art techniques enable multi-modal understanding and high-fidelity content generation.

Emerging challenges include robustness, versatility, and interactive intelligence.

Abstract

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.