ReAtCo improves text-guided video editing by using attention-map gradients to place edited objects in user-specified regions and by re-injecting the original background during diffusion sampling.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Re-Attentional Controllable Video Diffusion Editing
ReAtCo improves text-guided video editing by using attention-map gradients to place edited objects in user-specified regions and by re-injecting the original background during diffusion sampling.