2 papers
cs.CV2025
PoseTraj: Pose-Aware Trajectory Control in Video Diffusion
Longbin Ji, Lei Zhong, Pengfei Wei +1
Recent advancements in trajectory-guided video generation have achieved notable progress. However, existing models still face challenges in generating object motions with potential…
cs.CV2023
C2G2: Controllable Co-speech Gesture Generation with Latent Diffusion Model
Longbin Ji, Pengfei Wei, Yi Ren +3
Co-speech gesture generation is crucial for automatic digital avatar animation. However, existing methods suffer from issues such as unstable training and temporal inconsistency, p…