GeoWorld: Providing Full-frame Geometry Features to Facilitate 3D Scene Generation
Paper • 2511.23191 • Published • 6
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("peaes/GeoWorld", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]GeoWorld: Providing Full-frame Geometry Features to Facilitate 3D Scene Generation
This repository contains the model weights for GeoWorld, presented in the paper GeoWorld: Providing Full-frame Geometry Features to Facilitate 3D Scene Generation.
Authors: Yuhao Wan, Lijuan Liu, Jingzhi Zhou, Zihan Zhou, Xuying Zhang, Dongbo Zhang, Shaohui Jiao, Qibin Hou, Ming-Ming Cheng
Project Page | Paper(arXiv) | Code
TL;DR: GeoWorld uses a two-stage video-generation pipeline with full-frame geometry features to produce high-fidelity image-to-3D scenes faster than prior methods (7.5× faster than Hunyuan-Voyager).
Usage
Please refer to the official GitHub repository for installation instructions.
Citation
@article{wan2025geoworld,
title={GeoWorld: Unlocking the Potential of Geometry Models to Facilitate High-Fidelity 3D Scene Generation},
author={Wan, Yuhao and Liu, Lijuan and Zhou, Jingzhi and Zhou, Zihan and Zhang, Xuying and Zhang, Dongbo and Jiao, Shaohui and Hou, Qibin and Cheng, Ming-Ming},
journal={arXiv preprint arXiv:2511.23191},
year={2025}
}
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support