EUVIMEDEUVIMED entdecken
Crossref

ReGA: Relighting Dynamic Gaussian Avatars From Sparse Views

Lingzhe Zeng, Wensheng Li, Rongbin Zheng, Chengying Gao

IEEE Transactions on Circuits and Systems for Video Technology · 2026-04 · 36 (4) · 5011-5023

DOI: 10.1109/tcsvt.2025.3636679 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-04. Verfasst von Lingzhe Zeng und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 74 Literaturangaben. Gefördert von: National Key Research and Development Plan in China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dynamic human relighting is a complex task with significant demand across various applications. Its core challenge lies in effectively handling both dynamic human geometry reconstruction and material estimation. Existing works mainly achieve human reconstruction and relighting with Neural Radiance Fields, but they are not only inefficient, but also still inaccurate in material estimation and relighting. In this paper, we propose a novel approach called ReGA, which leverages efficient 3D Gaussian Splatting to create animatable and relightable avatars from sparse-view human motion. The training process consists of two stages: the geometry stage and the material stage. To overcome the geometric weakness of vanilla Gaussian representation, we introduce dynamic alignment mechanism in the geometry stage, combining the advantages of Gaussian splatting and mesh-based representation to produce reasonable human surface. In the material stage, we enhance the inverse rendering process by introducing twofold correlation strategies that establish chrominance correlation between Gaussian radiance color and albedo. Experiments demonstrate that our method outperforms existing approaches in dynamic human relighting task.

Förderung

  • National Key Research and Development Plan in China

Zitieren

APA

Zeng, L., Li, W., Zheng, R., & Gao, C. (2026). ReGA: Relighting Dynamic Gaussian Avatars From Sparse Views. IEEE Transactions on Circuits and Systems for Video Technology, 36(4), 5011-5023. https://doi.org/10.1109/tcsvt.2025.3636679

Vancouver

Zeng L, Li W, Zheng R, Gao C. ReGA: Relighting Dynamic Gaussian Avatars From Sparse Views. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(4):5011-5023. doi:10.1109/tcsvt.2025.3636679

BibTeX
@article{Zeng2026,
  author = {Zeng, Lingzhe and Li, Wensheng and Zheng, Rongbin and Gao, Chengying},
  title = {ReGA: Relighting Dynamic Gaussian Avatars From Sparse Views},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2026},
  volume = {36},
  number = {4},
  pages = {5011--5023},
  doi = {10.1109/tcsvt.2025.3636679}
}
Kostenlos starten →