fudan-generative-vision/champ
A diffusion-based human image animation system that generates coherent motion videos from a reference image using 3D parametric model guidance.
Not currently ranked — collecting fresh signals.
star history
Champ is a video generation model that animates a single human image by leveraging 3D parametric representations like SMPL to guide motion generation. The method ensures temporal consistency and user-controllable animation through parametric guidance, allowing precise control over generated human motion sequences. Released at ECCV 2024 with training code and sample data.
Frequently asked
- What is fudan-generative-vision/champ?
- A diffusion-based human image animation system that generates coherent motion videos from a reference image using 3D parametric model guidance.
- Is champ open source?
- Yes — fudan-generative-vision/champ is open source, released under the MIT license.
- What language is champ written in?
- fudan-generative-vision/champ is primarily written in Python.
- How popular is champ?
- fudan-generative-vision/champ has 4.3k stars on GitHub.
- Where can I find champ?
- fudan-generative-vision/champ is on GitHub at https://github.com/fudan-generative-vision/champ.