Continous Intermediate Token Learning - PyTorch implementation
September 19, 2023 ยท View on GitHub
Official Pytorch implementation of the CVPR2023 paper: Continuous Intermediate Token Learning with Implicit Motion Manifold for Keyframe Based Motion Interpolation
Prerequisites
- Python 3.10
- PyTorch 1.13.1 with CUDA
- NumPy v1.24.2
- transforms3d 0.4.1
Usage
train.py:
python train.py ["cmu"/"lafan"] [dataset path]
eval.py:
python eval.py ["cmu"/"lafan"] [dataset path] [ckpt]
A pre-trained CMU model can be found here.