Skip to main content
GameDev.net gamedev.net
2 sources covering this story

ARS-Avatar: Animatable and Relightable Surfel Avatars with Learnable Ambient Occlusion

arXiv cs.GR details ARS-Avatar, a surfel-based method for animatable, relightable human avatars from multi-view images under unknown lighting. The system adds deformation priors, deferred shading for BRDF estimation, and learnable ambient occlusion to better separate pose, material, and visibility. The goal is more faithful avatars that still hold up under new poses and lights.

First reported 2 weeks, 3 days ago • graphics ai avatars relighting
Want to discuss what this means for developers?
Open discussion

All Sources

View article page
PRIMARY SOURCE
arXiv cs.GR arXiv cs.GR

ARS-Avatar: Animatable and Relightable Surfel Avatars with Learnable Ambient Occlusion

2 weeks, 3 days ago Read source
arXiv cs.GR arXiv cs.GR 0% match

Heartian: Physiology-Aware Relightable Gaussian Head Avatar

2 weeks, 2 days ago Read source
Read Full Article Back to Feed