If you want a single place to track work on controllable 3D human avatar creation (priors, representations, and animation), this post acts like a living reading list.

The paper list below is rendered client-side by fetching a JSON file (so you can “import” new papers just by editing papers.json and refreshing the page).

preprint How to Build Digital Humans? From Priors to Photorealistic Avatars
Wojciech Zielonka, Tobias Kirschstein, Timo Bolkart, Simon Giebenhain, Vanessa Sklyarova, Xiang Deng, Donglai Xiang, Shunsuke Saito, Yebin Liu, Matthias Niessner, Justus Thies
Eurographics 2026 (State of the Art Report) · 2026
Digital HumansTaxonomyAvatarsPriorsAnimation
Project
journal From Bias to Balance: Leverage Representation Learning for Bias-Free MoCap Solving
Georgios Albanis, Nikolaos Zioulis, Spyridon Thermos, Anargyros Chatzitofis, Kostas Kolomvatsos
Computer Vision and Image Understanding · 2025
MoCapRepresentation LearningBiasDigital Humans
preprint On the Skinning of Gaussian Avatars
Nikolaos Zioulis, Nikolaos Kotarelas, Georgios Albanis, Spyridon Thermos, Anargyros Chatzitofis
arXiv preprint arXiv:2509.11411 · 2025
Radiance field-based methods have recently been used to reconstruct human avatars, showing that we can significantly downscale the systems needed for creating animated human avatars. With Gaussian splatting overcoming the challenges of slow rendering and backward mapping, a new family of approaches has emerged. However, the linear blend skinning required for the deformation of the Gaussians does not provide valid results for their non-linear rotation properties. This work addresses such artifacts in Gaussian avatar skinning.
Gaussian AvatarsSkinning3D Avatars
PDF

How to add new papers

Edit ./papers.json in this folder. Each entry can include:

  • id (string, unique)
  • title
  • authors (array of strings)
  • year (number)
  • venue (optional string)
  • type (preprint, conference, or journal; optional)
  • tags (array of strings, used for filtering)
  • links (optional object: pdf, project, doi)
  • abstract (optional string)
  • bibtex (optional string; enables the BibTeX modal)