A diffusion editing model, InstructMove, is trained on video frame pairs annotated by MLLMs using spatial conditioning, enabling non-rigid edits and viewpoint changes.
In- structpix2pix: Learning to follow image editing instructions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Instruction-based Image Manipulation by Watching How Things Move
A diffusion editing model, InstructMove, is trained on video frame pairs annotated by MLLMs using spatial conditioning, enabling non-rigid edits and viewpoint changes.