A self-supervised diffusion framework with a low-bitrate vector-quantization bottleneck learns disentangled motion and content latents supporting motion transfer and auto-regressive generation.
Hyperreenact: One-shot reenactment via jointly learning to refine and re- target faces
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
-
Bitrate-Controlled Diffusion for Disentangling Motion and Content in Video
A self-supervised diffusion framework with a low-bitrate vector-quantization bottleneck learns disentangled motion and content latents supporting motion transfer and auto-regressive generation.