|
--- |
|
license: mit |
|
pipeline_tag: image-to-3d |
|
tags: |
|
- image-to-3d |
|
--- |
|
|
|
|
|
# Isotropic3D |
|
|
|
Model card for *Isotropic3D: Image-to-3D Generation Based on a Single CLIP Embedding*. |
|
|
|
Project Page: https://isotropic3d.github.io/ |
|
|
|
arXiv: https://arxiv.org/abs/2403.10395 |
|
|
|
Source Code: https://github.com/pkunliu/Isotropic3D |
|
|
|
![mvd.png](https://cdn-uploads.huggingface.co/production/uploads/6463a5b51bb15fa38b0d5d2f/VTrn8zcRayQICjxvYeGKI.png) |
|
|
|
The model contains a diffusion model to generate multi-view images from single input image. |
|
|
|
## Citation |
|
|
|
``` |
|
@article{liu2024isotropic3d, |
|
title={Isotropic3D: Image-to-3D Generation Based on a Single CLIP Embedding}, |
|
author={Liu, Pengkun and Wang, Yikai and Sun, Fuchun and Li, Jiafang and Xiao, Hang and Xue, Hongxiang and Wang, Xinzhou}, |
|
journal={arXiv preprint arXiv:2403.10395}, |
|
year={2024} |
|
} |
|
``` |
|
|