Skip to content

Code of ECCV2024 Paper 《Decomposed Vector-Quantized Variational Autoencoder for Human Grasp Generation》

Notifications You must be signed in to change notification settings

MICLAB-BUPT/D-VQVAE

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 

Repository files navigation

DVQ-VAE Training and Generation

This repository contains code for training the DVQ-VAE model and generating dynamic grasps.

Usage Instructions

1. Train DVQ-VAE

Run the following command to train the DVQ-VAE model:

python DVQ-VAE/train_obman_mano_vertex.py

2. Generate Dynamic Grasps for Objects

To generate dynamic grasps for objects, run:

python DVQ-VAE/gen_HDMO_TTA.py

3. Generate Deformation GIFs

To generate deformation GIFs, run:

python DVQ-VAE-2/gen_deform_gif.py

About

Code of ECCV2024 Paper 《Decomposed Vector-Quantized Variational Autoencoder for Human Grasp Generation》

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published