Skip to content
Book Open access

LumaID: Harnessing Illumination-Awareness for High-Fidelity Video Head Identity Editing

Nov 2026 · Proceedings of the 34th ACM International Conference on Multimedia · 0 citations · 51 references

Abstract

Despite yielding higher visual quality than image-to-image approaches, masked generation paradigms for video face editing fundamentally lack attribute consistency (e.g., illumination, background). We introduce LumaID, a novel framework that explicitly disentangles identity and expression representations from environmental contexts, enabling high-fidelity, fine-grained video head editing while strictly preserving these crucial attributes. At its core, LumaID employs an Omni-Disentangled Diffusion Transformer (OD-DiT) that leverages 3D proxy representations to thoroughly isolate the source and target facial features, fundamentally preventing identity leakage and illumination degradation. To further overcome the distributional drift caused by proxy estimation noise and the lack of explicit consistency supervision, we propose Consist-GRPO. This post-training reinforcement learning mechanism formulates multi-dimensional reward signals (spanning identity, expression, pose, and lighting) to continuously steer the generative process toward strict spatiotemporal alignment. Extensive evaluations demonstrate that LumaID serves as a highly competitive baseline, exhibiting strong performance over prior approaches in both attribute consistency and overall visual quality. Project page: https://wyy27.github.io/LumaID/.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.