BodyReLux achieves photorealistic, temporally consistent full-body video relighting via a diffusion model with token-based lighting conditioning trained on a hybrid static-dynamic capture dataset.
arXiv preprint arXiv:2502.08590 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
HarmoVid trains a video diffusion model on deflickered paired data from real and synthetic videos using asymmetric alpha mask conditioning to produce temporally coherent relightful portrait harmonization.
citing papers explorer
-
BodyReLux: Temporally Consistent Full-Body Video Relighting
BodyReLux achieves photorealistic, temporally consistent full-body video relighting via a diffusion model with token-based lighting conditioning trained on a hybrid static-dynamic capture dataset.
-
HarmoVid: Relightful Video Portrait Harmonization
HarmoVid trains a video diffusion model on deflickered paired data from real and synthetic videos using asymmetric alpha mask conditioning to produce temporally coherent relightful portrait harmonization.