MotionAdapter transfers reference video motions into target videos inside DiT diffusion models by isolating attention-derived motion fields and refining them via DINO-guided semantic alignment.
Exploring the limits of transfer learning with a unified text-to-text transformer.JMLR, pages 1–67
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
-
MotionAdapter: Video Motion Transfer via Content-Aware Attention Customization
MotionAdapter transfers reference video motions into target videos inside DiT diffusion models by isolating attention-derived motion fields and refining them via DINO-guided semantic alignment.