You can create an anaconda environment called argus-3d
using
conda env create -f environment.yaml
conda activate argus-3d
Next, compile the extension modules. You can do this via
python setup.py build_ext --inplace
Download stage1 checkpoint and place it into output/PR256_ED512_EN8192
.
Download stage2 checkpoint and place it into output/PR256_ED512_EN8192/class-guide/transformer3072_24_32
.
Then you can try class-guide generation by run:
python generate_class-guide.py --batch_size 16 --cate chair
This script should create a folder output/PR256_ED512_EN8192/class-guide/transformer3072_24_32/class_cond
where the output meshes are stored.
Note: Our model requires significant memory, and it's recommended to run it on a GPU with high VRAM capacity (40GB or above). Generating a single mesh on the A100 (80GB) takes approximately 50 seconds on average, while on V100 (32GB) it takes ~6 minutes.
The occupancies, point clouds, and supplementary rendered images based on the Objaverse dataset can be downloaded from https://huggingface.co/datasets/BAAI/Objaverse-MIX
- Image-guide generation
- Text-guide generation
- Training code
Thanks to everyone who makes their code and models available.
Thanks for open-sourcing!
@misc{yu2023pushing,
title={Pushing the Limits of 3D Shape Generation at Scale},
author={Yu Wang and Xuelin Qian and Jingyang Huo and Tiejun Huang and Bo Zhao and Yanwei Fu},
year={2023},
eprint={2306.11510},
archivePrefix={arXiv},
primaryClass={cs.CV}
}