NVIDIA and USC's HorizonRelight brings consistent relighting to long videos
NVIDIAAI · x · 2026-09-11
NVIDIA Research and USC present HorizonRelight (ECCV 2026), tackling lighting jumps when diffusion video models relight long videos in chunks. By reframing long-horizon relighting as temporally conditioned latent domain translation—propagating target-domain latents across sliding-window chunks with masked self-conditioning and a warm-start prompt anchor—the method markedly improves temporal consistency and removes chunk-boundary artifacts. Code is coming soon.
Related event: NVIDIA and USC Release HorizonRelight for Consistent Video Relighting(2 posts)→
More from Multimodal
- TischEins, a large Midjourney SREF library, relaunches with new design after security outage — tisch_eins · 2026-10-26
- MOSS-Image-SFT 4-step distillation tops 16.5K downloads on Hugging Face — _akhaliq · 2026-10-26
- Claude Code can now edit videos: a 10-prompt workflow from raw footage to final cut — TawohAwa · 2026-10-26
- One-sentence 3D worlds turn cinematic with CineMap and TapNow — gizakdag · 2026-10-26
- No Camera Needed: Creator Builds an Entire World in CineMap and Directs It Into Cinema — gizakdag · 2026-10-26
- Kling vs. Seedance: the Chinese AI video model rivalry — DavidmComfort · 2026-10-26