ElasticTTT: Prior-Preserving Test-Time Tuning for Video Editing
Merged summary
TL;DR - ElasticTTT is a test-time tuning framework for one-shot video editing that prevents pretrained diffusion models from collapsing toward the source video. It preserves the model’s generative prior while improving edit fidelity and protecting unchanged regions.
- Identifies “Prior Collapse,” where standard single-point optimization causes lost text conditioning, source-video memorization, or entangled regional features.
- Uses Target Distribution Regularization to discourage sharp memorization minima.
- Introduces Contrastive CFG to steer generation away from source bias.
- Applies an Asynchronous Noise Schedule to preserve unedited regions and reports state-of-the-art performance in extensive evaluations.
Sources (1)
ElasticTTT: Prior-Preserving Test-Time Tuning for Video Editing
TL;DR - ElasticTTT is a test-time tuning framework for one-shot video editing that prevents pretrained diffusion models from collapsing toward the source video. It preserves the model’s generative prior while improving edit fidelity and protecting unchanged regions.
- Identifies “Prior Collapse,” where standard single-point optimization causes lost text conditioning, source-video memorization, or entangled regional features.
- Uses Target Distribution Regularization to discourage sharp memorization minima.
- Introduces Contrastive CFG to steer generation away from source bias.
- Applies an Asynchronous Noise Schedule to preserve unedited regions and reports state-of-the-art performance in extensive evaluations.