A training-free method combines mask normalization and temporal intrinsic denoising to improve trajectory control and perceptual quality in text-to-video diffusion.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Interactive Video Generation via Domain Adaptation
A training-free method combines mask normalization and temporal intrinsic denoising to improve trajectory control and perceptual quality in text-to-video diffusion.