Gen4P
adapting video generators for 4D perception
1 min readupdated
Gen4P turns a video generator into a tool for full 4D scene perception. The model handles 3D point tracking, video depth estimation, camera pose estimation, and dense 4D visualization. The architecture combines a Wan2.1 video foundation, a frozen DVD depth prior module, and a query decoder. This solution is ideal for researchers and developers working with computer vision and video analysis.
Key features
- Built on the Wan2.1 video generator
- Supports 3D point tracking in video
- Includes a DVD depth prior module
- Enables camera pose estimation
What you can do
- Run point tracking to analyze motion in videos
- Perform frame depth estimation to build 3D structures
- Determine camera motion trajectories and poses in video
Example
hf download yitongx/Gen4P gen4p.pth --local-dir ckpt
hf download FayeHongfeiZhang/DVD dvd_1.1.safetensors --local-dir ckptRead more
DetailsLicense: CC BY-NC 4.0
Base model: Wan2.1
Components: Wan2.1, DVD depth prior, query decoder








Comments