Update README.md
Browse files
README.md
CHANGED
|
@@ -11,7 +11,7 @@ datasets:
|
|
| 11 |
- wjwow/FreeMan
|
| 12 |
---
|
| 13 |
# SkeletonDiffusion Model Card
|
| 14 |
-
This model card focuses on the model associated with the SkeletonDiffusion model, from _Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction_, codebase available [here](https://github.com/Ceveloper/SkeletonDiffusion/tree/main).
|
| 15 |
|
| 16 |
SkeletonDiffusion is a probabilistic human motion prediction model that takes as input 0.5s of human motion and generates future motions of 2s with a inference time of 0.4s.
|
| 17 |
SkeletonDiffusion generates motions that are at the same time realistic and diverse. It is a latent diffusion model that with a custom graph attention architecture trained with nonisotropic Gaussian diffusion.
|
|
@@ -33,4 +33,4 @@ You can use the model for purposes under the BSD 2-Clause License.
|
|
| 33 |
|
| 34 |
### Train and Inference
|
| 35 |
|
| 36 |
-
Please refer to our [GitHub](https://github.com/Ceveloper/SkeletonDiffusion/tree/main) codebase for both usecases.
|
|
|
|
| 11 |
- wjwow/FreeMan
|
| 12 |
---
|
| 13 |
# SkeletonDiffusion Model Card
|
| 14 |
+
This model card focuses on the model associated with the SkeletonDiffusion model, from _Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction_, [arxiv](https://arxiv.org/abs/2501.06035), codebase available [here](https://github.com/Ceveloper/SkeletonDiffusion/tree/main).
|
| 15 |
|
| 16 |
SkeletonDiffusion is a probabilistic human motion prediction model that takes as input 0.5s of human motion and generates future motions of 2s with a inference time of 0.4s.
|
| 17 |
SkeletonDiffusion generates motions that are at the same time realistic and diverse. It is a latent diffusion model that with a custom graph attention architecture trained with nonisotropic Gaussian diffusion.
|
|
|
|
| 33 |
|
| 34 |
### Train and Inference
|
| 35 |
|
| 36 |
+
Please refer to our [GitHub](https://github.com/Ceveloper/SkeletonDiffusion/tree/main) codebase for both usecases.
|