2 papers
cs.CV2026
Diffusion Path Alignment for Long-Range Motion Generation and Domain Transitions
Haichao Wang, Alexander Okupnik, Yuxing Han +3
Long-range human movement generation remains a central challenge in computer vision and graphics. Generating coherent transitions across semantically distinct motion domains remain…
cs.CV2026
Beyond Boundary Frames: Talking-Head Inbetweening via Context-Aware Motion Modeling
Yuchen Deng, Xiuyang Wu, Hai-Tao Zheng +4
Existing talking-head generation methods primarily target open-ended generation rather than bridging two existing video segments. In this paper, we study talking-head inbetweening,…