LucidFusion
Hao He Yixun Liang, Luozhou Wang, Yuanhao Cai, Xinli Xu, Hao-Xiang Guo, Xiang Wen, Yingcong Chen
Model source
- Kind
- Other
- File size
- 309 KB–3.23 GB
- Version
- vRevision 24de120
- Updated
- Sep 15, 2026
- Downloads
- 0
- Source
- Hugging Face
Source excerpt
Hao He Yixun Liang, Luozhou Wang, Yuanhao Cai, Xinli Xu, Hao-Xiang Guo, Xiang Wen, Yingcong Chen
Sources
1 source
Sources
1 sourceVerified Sep 1
Download files
Model artifacts
4 artifacts
Model artifacts
4 artifactsgsdecoder/diffusion_pytorch_model.safetensors
safetensors · 338 MB · SHA-256 32f6676f9d8d…673b · Hugging Face
Download fileunet/diffusion_pytorch_model.safetensors
safetensors · 3.23 GB · SHA-256 b41e0dda433b…6da4 · Hugging Face
Download filevae/diffusion_pytorch_model.safetensors
safetensors · 319 MB · SHA-256 8e28a6905de3…e28b · Hugging Face
Download fileSource excerpts
2 excerpts
Source excerpts
2 excerpts--- license: mit pipeline_tag: image-to-3d tags: - image-to-3d --- # LucidFusion: Generating 3D Gaussians with Arbitrary Unposed Images [Hao He*](https://heye0507.github.io/) [Yixun Liang*](https://yixunliang.github.io/), [Luozhou Wang](https://wileewang.github.io/), [Yuanhao Cai](https://github.com/caiyuanhao1998), [Xinli Xu](https://scholar.google.com/citations?user=lrgPuBUAAAAJ&hl=en&inst=1381320739207392350), [Hao-Xiang Guo](), [Xiang Wen](), [Yingcong Chen**](https://www.yingcong.me) \*: Equal contribution. \**: Corresponding author. [Paper PDF](https://arxiv.org/abs/2410.15636) | [Project Page](https://heye0507.github.io/LucidFusion_page/) | [Gradio Demo](Coming Soon) --- ### Demo results of our latest model <style> .gif-row { display: flex; justify-content: center; flex-wrap: wrap; gap: 10px; /* Adjust the gap as needed */ } .gif-row img { width: 20%; /* Adjust width to control size */ } </style> <div class="gif-row"> <img src="resources/res_ironman.gif" alt="Ironman"> <img src="resources/res_hulk.gif" alt="Hulk"> <img src="resources/res_deadpool.gif" alt="Deadpool"> <img src="resources/res_team_america.gif" alt="Team America"> </div> <div class="gif-row"> <img src="resources/res_venom_1.gif" alt="Venom"> <img src="resources/res_black_widow.gif" alt="Black Widow"> <img src="resources/res_spiderman.gif" alt="Spiderman"> <img src="resources/res_superman.gif" alt="Superman"> </div> <div class="gif-row"> <img src="resources/res_minions.gif" alt="Minions"> <img src="resources/res_snowman.gif" alt="Snowman"> <img src="resources/res_d2_witch.gif" alt="Diablo 2"> <img src="resources/res_harry_porter.gif" alt="Harry Porter"> </div> <div class="gif-row"> <img src="resources/princess.gif" alt="Princess"> <img src="resources/res_arabic.gif" alt="Arabic"> <img src="resources/res_chief.gif" alt="Chief"> <img src="resources/res_knight.gif" alt="Knight"> </div> <div class="gif-row"> <img src="resources/res_cry_witch.gif" alt="Witch"> <img src="resources/boy_running.gif" alt="Boy"> <img src="resources/girl_head_3.gif" alt="Girl Head"> <img src="resources/girl_head_2.gif" alt="Girl Head 2"> </div> <div align=center> <p style="max-width: 1000px;"> We present a flexible end-to-end feed-forward framework, named the <i>LucidFusion</i>, to generate high-resolution 3D Gaussians from unposed, sparse, and arbitrary numbers of multi...
Source context: 0 downloads · 14 likes · Pipeline image-to-3d · Library diffusers · Repo heye0507/LucidFusion
