Update README.md
Browse files
README.md
CHANGED
|
@@ -21,7 +21,11 @@ Global
|
|
| 21 |
|
| 22 |
### Use Case:
|
| 23 |
EgoHand could be used by researchers and engineers working on egocentric hand pose estimation to produce accurate 3D hand keypoints and MHR/SOMA-hand mesh parameters from single RGB crops. The resulting 3D hand pose/keypoint data serves as a training signal for downstream robotics applications — particularly robotic foundation models and manipulation policy training, where accurate hand trajectories human demonstration video are needed to supervise or bootstrap policy learning.
|
| 24 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
## Model Architecture:
|
| 27 |
**Architecture Type:** Transformer
|
|
|
|
| 21 |
|
| 22 |
### Use Case:
|
| 23 |
EgoHand could be used by researchers and engineers working on egocentric hand pose estimation to produce accurate 3D hand keypoints and MHR/SOMA-hand mesh parameters from single RGB crops. The resulting 3D hand pose/keypoint data serves as a training signal for downstream robotics applications — particularly robotic foundation models and manipulation policy training, where accurate hand trajectories human demonstration video are needed to supervise or bootstrap policy learning.
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
## References:
|
| 27 |
+
[EgoHand inference pipeline](https://github.com/NVIDIA/IsaacCapture/tree/main/src/python/isaaccapture_egopost)
|
| 28 |
+
[EgoHand model finetuning](https://github.com/NVlabs/GEM-X)
|
| 29 |
|
| 30 |
## Model Architecture:
|
| 31 |
**Architecture Type:** Transformer
|