RelightAnyone: A Generalized Relightable 3D Gaussian Head Model

Disney Research’s new head-relighting model removes a big capture bottleneck: you no longer need OLAT footage for every subject. It can learn from ordinary single- or multi-view images, then generalize to relight new heads under different scene lighting. For avatar pipelines, that means less specialized capture and a much easier path to usable relightable characters.