TEACH: Temporal Action Compositions for 3D Humans
2023-01-23
Official PyTorch implementation of the paper "TEACH: Temporal Action Compositions for 3D Humans".
This implementation:
- Instruction on how to prepare the datasets used in the experiments.
- The training code:
- For both baselines
- For TEACH method
- A simple interacting demo that given some prompts with texts and durations returns back:
- a
npyfile containing the vertices of the body generated by TEACH. - a video that demonstrates the result.
- a
| Author(s): | Athanasiou Nikolaos and Petrovich Mathis and Michael J. Black and Varol Gül |
| Department(s): |
Perceiving Systems |
| Research Projects(s): |
Language and Movement Modeling Human Movement |
| Publication(s): |
{TEACH}: {T}emporal {A}ction {C}omposition for 3{D} {H}umans
|
| Authors: | Athanasiou Nikolaos and Petrovich Mathis and Michael J. Black and Varol Gül |
| Release Date: | 2023-01-23 |
| Repository: | https://github.com/athn-nik/teach |
