A coarse-to-fine audio-driven animation framework that uses pose-guided refinement and hand-specific reward learning to generate long, identity-stable talking videos.
E.; Fang, Y.; Lee, H.-Y.; Ren, J.; Yang, M.-H.; et al
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
-
InfinityHuman: Towards Long-Term Audio-Driven Human
A coarse-to-fine audio-driven animation framework that uses pose-guided refinement and hand-specific reward learning to generate long, identity-stable talking videos.