|
|
--- |
|
|
license: other |
|
|
license_name: slab |
|
|
license_link: LICENSE |
|
|
--- |
|
|
|
|
|
# 3DEnhancer |
|
|
|
|
|
[Project Page](https://yihangluo.com/projects/3DEnhancer/) | [Arxiv](https://arxiv.org/abs/2412.18565) | [Demo](https://huggingface.co/spaces/yslan/3DEnhancer) |
|
|
|
|
|
This repo contains the pretrained weights for *3DEnhancer: Consistent Multi-View Diffusion for 3D Enhancement*. |
|
|
|
|
|
*3DEnhancer employs a multi-view diffusion model to enhance multi-view images, thus improving 3D models.* |
|
|
|
|
|
## Usage |
|
|
|
|
|
To download the model: |
|
|
```python |
|
|
from huggingface_hub import hf_hub_download |
|
|
ckpt_path = hf_hub_download(repo_id="Luo-Yihang/3DEnhancer", filename="model.safetensors") |
|
|
``` |
|
|
Please refer to our [repo](https://github.com/Luo-Yihang/3DEnhancer) for more details on loading and inference. |
|
|
|
|
|
## Citation |
|
|
|
|
|
``` |
|
|
@article{luo20243denhancer, |
|
|
title={3DEnhancer: Consistent Multi-View Diffusion for 3D Enhancement}, |
|
|
author={Yihang Luo and Shangchen Zhou and Yushi Lan and Xingang Pan and Chen Change Loy}, |
|
|
booktitle={arXiv preprint arXiv:2412.18565} |
|
|
year={2024}, |
|
|
} |
|
|
``` |
