Spaces:
Running on Zero
Running on Zero
|
Download README.md from ceccurr/SkeletonDiffusion: direct link, hf CLI and curl.
- Browser
- Download file 1.06 kB
-
https://huggingface.co/spaces/ceccurr/SkeletonDiffusion/resolve/main/README.md
- Command line
-
hf download hf://spaces/ceccurr/SkeletonDiffusion/README.md
-
curl -L -o README.md https://huggingface.co/spaces/ceccurr/SkeletonDiffusion/resolve/main/README.md
1.06 kB
| title: SkeletonDiffusion | |
| emoji: 馃捇 | |
| colorFrom: purple | |
| colorTo: green | |
| sdk: gradio | |
| sdk_version: 5.24.0 | |
| app_file: app.py | |
| pinned: false | |
| short_description: Realistic 3D human motion prediction (CVPR 2025) | |
| license: bsd-2-clause | |
| models: | |
| - SkeletonDiffusion/ModelCheckpoints | |
| tags: | |
| - human-motion-prediction | |
| - diffusion | |
| - arxiv:2501.06035 | |
| run: | | |
| bash setup.sh | |
| python app.py | |
| # SkeletonDiffusion demo | |
| Demo of **SkeletonDiffusion** from _Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction_ (CVPR 2025): | |
| probabilistic prediction of 2 s of future human motion from 0.5 s of observed motion. | |
| [Paper](https://arxiv.org/abs/2501.06035) 路 [Hugging Face paper page](https://huggingface.co/papers/2501.06035) 路 [Code](https://github.com/Ceveloper/SkeletonDiffusion) 路 [Model](https://huggingface.co/SkeletonDiffusion/ModelCheckpoints) | |
| See also the follow-up work **EquiFusion** (ECCV 2026), kinematics-agnostic motion prediction for any skeleton: [Paper](https://arxiv.org/abs/2607.10984) 路 [Code](https://github.com/Ceveloper/EquiFusion) | |