DualReal jointly trains identity and motion adapters for video customization, reporting a 21.7% CLIP-I and 31.8% DINO-I improvement over existing methods.
Still-moving: Customized video generation without customized video data
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
-
DualReal: Adaptive Joint Training for Lossless Identity-Motion Fusion in Video Customization
DualReal jointly trains identity and motion adapters for video customization, reporting a 21.7% CLIP-I and 31.8% DINO-I improvement over existing methods.