FRVD warps a source face toward driving poses with implicit keypoints, then repairs lost details inside Stable Video Diffusion's latent space, reporting gains over seven baselines on large-pose reenactment benchmarks.
Taming transformers for high-resolution image synthesis
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Navigating Large-Pose Challenge for High-Fidelity Face Reenactment with Video Diffusion Model
FRVD warps a source face toward driving poses with implicit keypoints, then repairs lost details inside Stable Video Diffusion's latent space, reporting gains over seven baselines on large-pose reenactment benchmarks.