Hong Kong University of Science and Technology et al. · Text-to-Video

Diffusion as Shader (DaS)

A 3D-aware video diffusion model that enables versatile video generation control through 3D tracking signals, supporting mesh-to-video generation, camera control, motion transfer, and object manipulation within a unified architecture. Achieves strong results with minimal fine-tuning (3 days on 8 H800 GPUs, <10k videos).