How to Build Digital Humans? From Priors to Photorealistic Avatars

2026-07-05

AI Summary

This work addresses the challenge of constructing controllable and photorealistic 3D digital humans by systematically tackling core issues in appearance and motion modeling. It introduces a multidimensional taxonomy that integrates body-region segmentation with types of prior knowledge, offering a comprehensive overview of research advances and shared principles across full-body, head-centric, and hierarchical representations—including hands, hair, and clothing. By synthesizing learning-based human priors, personalized avatar generation, and layered geometric and appearance modeling techniques, the study establishes a clear technical roadmap. Beyond providing a structured survey of key literature, it explicitly identifies open problems and future research directions, thereby offering an efficient entry point for newcomers to the field.

Abstract

This state-of-the-art report provides an overview of controllable 3D human avatar creation. We describe current 3D avatar systems, which typically consist of three stages: (i) learning priors of human appearance and motion, (ii) creating a personalized avatar, and (iii) animating the avatar. To limit the scope, we focus on the prior learning and avatar creation stages. We define current avatar representations and introduce a taxonomy that categorizes existing work along multiple axes, including body regions and employed priors. We review methods for full-body and head avatars, as well as layered representations that decompose the body into components such as hands, hair, and garments. Finally, we outline common underlying principles, reference key literature for newcomers, and discuss open challenges and future research directions.

Problem

• digital humans
• 3D avatars
• photorealistic avatars
• prior learning
• avatar creation

Innovation

• 3D human avatars
• prior learning
• avatar representation
• layered decomposition
• controllable digital humans