Relit-LiVE jointly predicts relit videos and viewpoint-aligned environment maps inside a single diffusion process to achieve physically consistent video relighting without camera pose input.
arXiv preprint arXiv:2302.01334 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Relit-LiVE: Relight Video by Jointly Learning Environment Video
Relit-LiVE jointly predicts relit videos and viewpoint-aligned environment maps inside a single diffusion process to achieve physically consistent video relighting without camera pose input.