Downloads · 30 days
3
6% of all-time downloads
heye0507/LucidFusion
LucidFusion is a image-to-3d model from heye0507. Use it for the image-to-3d task on the model card, and read the license before you ship it in a product. It is set up for diffusers. The card lists the license as mit.
Hao He Yixun Liang, Luozhou Wang, Yuanhao Cai, Xinli Xu, Hao-Xiang Guo, Xiang Wen, Yingcong Chen
Downloads · 30 days
3
6% of all-time downloads
All-time downloads
50
Public
Parameters
866M
27.9 GB on disk
Likes
14
Public
Click a slice to open those files.
.safetensors4.2 GB · 97%
From the Hugging Face model README
Hao He* Yixun Liang*, Luozhou Wang, Yuanhao Cai, Xinli Xu, Hao-Xiang Guo, Xiang Wen, Yingcong Chen**
*: Equal contribution. **: Corresponding author.
Paper PDF | Project Page | [Gradio Demo](Coming Soon)
Examples of cross-dataset content creations with our framework, the LucidFusion, around ~13FPS on A800.
</div>We present a flexible end-to-end feed-forward framework, named the LucidFusion, to generate high-resolution 3D Gaussians from unposed, sparse, and arbitrary numbers of multiview images.
<details><summary>CLICK for the full abstract</summary></details>Recent large reconstruction models have made notable progress in generating high-quality 3D objects from single images. However, these methods often struggle with controllability, as they lack information from multiple views, leading to incomplete or inconsistent 3D reconstructions. To address this limitation, we introduce LucidFusion, a flexible end-to-end feed-forward framework that leverages the Relative Coordinate Map (RCM). Unlike traditional methods linking images to 3D world thorough pose, LucidFusion utilizes RCM to align geometric features coherently across different views, making it highly adaptable for 3D generation from arbitrary, unposed images. Furthermore, LucidFusion seamlessly integrates with the original single-image-to-3D pipeline, producing detailed 3D Gaussians at a resolution of $512 \times 512$, making it well-suited for a wide range of applications.
Our inference code is now released!
Please refer to our repo for more details.
Our current model loads pre-trained diffusion model for config. We use stable-diffusion-2-1-base, to download it, simply run
python pretrained/download.py
You can omit this step if you already have stable-diffusion-2-1-base, and simply update "model_key" with your local SD-2-1 path for scripts in scripts/ folder.
Our pre-trained weights is released!
If you find our work useful, please consider citing our paper.
@misc{he2024lucidfusion,
title={LucidFusion: Generating 3D Gaussians with Arbitrary Unposed Images},
author={Hao He and Yixun Liang and Luozhou Wang and Yuanhao Cai and Xinli Xu and Hao-Xiang Guo and Xiang Wen and Yingcong Chen},
year={2024},
eprint={2410.15636},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2410.15636},
}
This work is built on many amazing research works and open-source projects:
Thanks for their excellent work and great contribution to 3D generation area.