NASA.PyTorch
This is a PyTorch implementation of NASA: Neural Articulated Shape Approximation
Requirements
Dataset Processing
Training
CUDA_VISIBLE_DEVICES=1 python train_net_light.py -cfg ../configs/pl_w_sk.yaml -- \
Related works
- AMASS: Archive of Motion Capture as Surface Shapes
- Expressive Body Capture: 3D Hands, Face, and Body from a Single Image
- Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion
Contact
The code in this repository is developed by Yuliang Xiu