How to Build Digital Humans? From Priors to Photorealistic Avatars
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.
Authors
- Simon Giebenhain (ORCID: https://orcid.org/0000-0002-7588-8767)
- Donglai Xiang (ORCID: https://orcid.org/0000-0002-6487-1935)
- Timo Bolkart (ORCID: https://orcid.org/0000-0002-3829-3924)
- Vanessa Sklyarova (ORCID: https://orcid.org/0000-0002-8883-9972)
- Justus Thies (ORCID: https://orcid.org/0000-0002-0056-9825)
- Tobias Kirschstein (ORCID: https://orcid.org/0009-0002-5308-591X)
- Matthias Nießner (ORCID: https://orcid.org/0000-0001-6093-5199)
- Yebin Liu
- Shunsuke Saito (ORCID: https://orcid.org/0000-0003-2053-3472)
- Wojciech Zielonka
- Xiang Deng
Institutions
- Google (United States) (US)
- Nvidia (United Kingdom) (GB)
- Technische Universität Darmstadt (DE)
- ETH Zurich (CH)
- Nvidia (United States) (US)
- Max Planck Institute for Intelligent Systems (DE)
- Technical University of Munich (DE)
- Tsinghua University (CN)
Publication Details
- Journal
- Computer Graphics Forum
- Published
- 2026-11-04
- DOI
- https://doi.org/10.1111/cgf.70395
- Primary Topic
- 3D Shape Modeling and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.00