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.
Over++: Generative video compositing for layer interaction effects.arXiv preprint arXiv:2512.19661, 2025
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
-
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.