MoDiT, a diffusion transformer conditioned on 3DMM coefficients and Wav2Lip references, produces talking-head videos with improved same-identity lip sync and more natural blinks in its reported benchmarks.
A morphable model for the synthesis of 3d 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
-
MoDiT: Learning Highly Consistent 3D Motion Coefficients with Diffusion Transformer for Talking Head Generation
MoDiT, a diffusion transformer conditioned on 3DMM coefficients and Wav2Lip references, produces talking-head videos with improved same-identity lip sync and more natural blinks in its reported benchmarks.