2 papers
cs.CV2026
A Novel FACS-Aligned Anatomical Text Description Paradigm for Fine-Grained Facial Behavior Synthesis
Jiahe Wang, Cong Liang, Xuandong Huang +5
Facial behavior constitutes the primary medium of human nonverbal communication. Existing synthesis methods predominantly follow two paradigms: coarse emotion category labels or on…
cs.CV2025
ConsistTalk: Intensity Controllable Temporally Consistent Talking Head Generation with Diffusion Noise Search
Zhenjie Liu, Jianzhang Lu, Renjie Lu +2
Recent advancements in video diffusion models have significantly enhanced audio-driven portrait animation. However, current methods still suffer from flickering, identity drift, an…