Downloads · 30 days
0
Andrettiaaa/Pixal3D
Pixal3D is a image-to-3d model from Andrettiaaa. Use it for the image-to-3d task on the model card, and read the license before you ship it in a product. The card lists the license as other.
Downloads · 30 days
0
Access
Public
Updated May 17, 2026
Repo size
24 GB
Likes
0
Public
Click a slice to open those files.
.safetensors24 GB · 100%
From the Hugging Face model README
Dong-Yang Li¹ · Wang Zhao²* · Yuxin Chen² · Wenbo Hu² · Meng-Hao Guo¹ · Fang-Lue Zhang³ · Ying Shan² · Shi-Min Hu¹✉
¹Tsinghua University (BNRist) ²Tencent ARC Lab ³Victoria University of Wellington
*Project lead ✉Corresponding author
</div> <div align="center"> <a href="https://ldyang694.github.io/projects/pixal3d/"><img src=https://img.shields.io/badge/Project%20Page-333399.svg?logo=googlehome height=22px></a> <a href="https://huggingface.co/spaces/TencentARC/Pixal3D"><img src=https://img.shields.io/badge/%F0%9F%A4%97%20Demo-276cb4.svg height=22px></a> <a href="https://github.com/TencentARC/Pixal3D"><img src=https://img.shields.io/badge/Code-Github-black.svg?logo=github height=22px></a> <a href="https://arxiv.org/abs/2605.10922"><img src=https://img.shields.io/badge/Arxiv-b5212f.svg?logo=arxiv height=22px></a> </div>Pixal3D generates high-fidelity 3D assets from a single image. Unlike previous methods that loosely inject image features via attention, Pixal3D explicitly lifts pixel features into 3D through back-projection, establishing direct pixel-to-3D correspondences. This enables near-reconstruction-level fidelity with detailed geometry and PBR textures.
| Branch | Description |
|---|---|
main | Latest version — improved implementation based on Trellis.2 backbone with better performance. |
paper | Paper version — original implementation based on Direct3D-S2, corresponding to results reported in our SIGGRAPH 2026 paper. |
If you want to reproduce the results in our paper, please switch to the
paperbranch.
You can try Pixal3D directly in your browser without any installation via our Hugging Face Gradio demo:
Please first follow the installation guide of TRELLIS.2 to set up the base environment.
pip install -r requirements.txt
pip install https://github.com/LDYang694/Storages/releases/download/20260430/utils3d-0.0.2-py3-none-any.whl
Generate a GLB mesh from a single image:
python inference.py --image assets/test_image/0.png --output ./output.glb
We provide a Gradio web demo for Pixal3D, which allows you to generate 3D meshes from images interactively.
python app.py
This project is heavily built upon Trellis.2 and Direct3D-S2. We also thank the following repos for their great contributions: Trellis.
If you find this work useful, please consider citing:
@article{li2026pixal3d,
title = {Pixal3D: Pixel-Aligned 3D Generation from Images},
author = {Li, Dong-Yang and Zhao, Wang and Chen, Yuxin and Hu, Wenbo and Guo, Meng-Hao and Zhang, Fang-Lue and Shan, Ying and Hu, Shi-Min},
journal = {arXiv preprint arXiv:2605.10922},
year = {2026}
}