tags: - video-generation - video-relighting - diffusion arxiv: 2605.06658

Relit-LiVE: Relight Video by Jointly Learning Environment Video

Relit-LiVE is A physically consistent and temporally stable video relighting framework that jointly predicts relit videos and viewpoint-aligned per-frame warped environment maps, without requiring prior camera poses.

This repository hosts the released Relit-LiVE checkpoints.

Links

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for weiqingXiao/Relit-LiVE