AI Paper Atlas

Research map / Video / Video generation

Light-A-Video: Training-free Video Relighting via Progressive Light Fusion

Yujie Zhou, Jiazi Bu, Pengyang Ling, Pan Zhang, Tong Wu, Qidong Huang, Jinsong Li, Xiaoyi Dong, Yuhang Zang, Yuhang Cao, Anyi Rao, Jiaqi Wang and 1 more

ICCV 2025 · Video › Video generation · approach: Diffusion-based video editing · 29 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
apply Light-A-Video (CLA + PLF with video diffusion prior) instead of per-frame IC-LightIC-Light · Video relighting test settemporal CLIP score: 0.9040 -> 0.9667Improved
apply Light-A-Video instead of per-frame IC-LightIC-Light · Video relighting test setmotion preservation: 5.969 -> 1.833Improved
apply Light-A-Video instead of per-frame IC-LightIC-Light · User studyVideo Smoothness: 2.128 -> 3.502Improved
use Light-A-Video instead of SDEdit with 0.2 noiseIC-Light · Video relighting test setFID: 13.79 -> 29.63Hurt
add more noise (SDEdit 0.6) for temporal smoothingIC-Light + SDEdit · Video relighting test setID preservation: FID 13.79 -> 62.61Hurt
add Consistent Light Attention (CLA) to IC-Light (ablation)Light-A-Video · qualitative ablation with background generationlighting source stabilityImproved
add Progressive Light Fusion (PLF) with video diffusion priors (ablation)Light-A-Video · qualitative ablationtemporal smoothness of relit appearanceImproved
use decaying fusion weight lambda_t in PLF instead of constant lambda_t = 1 (ablation)PLF · FID, temporal CLIP and motion preservationFID / motion preservationImproved
increase CLA trade-off gamma to large values (ablation)CLA · FID versus gammaFIDHurt
use CLA gamma between 0.2 and 0.5 (ablation)CLA · FID and motion preservationFID / motion preservationImproved

Later papers that compared with this method

3 later accepted papers report Light-A-Video as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy