README.md

metadata

title: Extend3D
emoji: 🧩
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 5.34.2
python_version: '3.10'
app_file: app.py
suggested_hardware: a10g-large
tags:
  - 3d-generation
  - image-to-3d
  - gaussian-splatting
  - mesh
short_description: '[CVPR 2026] Extend3D: Town-Scale 3D Generation'
pinned: false

Extend3D: Town-scale 3D Generation

CVPR 2026

Seungwoo Yoon, Jinmo Kim, Jaesik Park
Seoul National University

🛠 Preparation

Environment

• Linux x86-64 system
• NVIDIA GPU with 24GB VRAM ($a=b=2$)
• CUDA version ≥ 12.4

Larger scene generation may require more VRAM.

Install

conda create -n extend3d python=3.10
conda activate extend3d
pip install -r requirements.txt

If your GPU does not support pytorch-2.4.0, follow instructions in SETUP.md.

🚀 Usage

Quick Start

from extend3d import Extend3D
from PIL import Image
import imageio

from trellis.utils import render_utils, postprocessing_utils

pipeline = Extend3D.from_pretrained("microsoft/TRELLIS-image-large").cuda()
image = Image.open("assets/examples/0.png")

output = pipeline.run(image)

video = render_utils.render_video(output['gaussian'][0], r=1.6, resolution=1024)['color']

imageio.mimsave('sample_gs.mp4', video, fps=30)

glb = postprocessing_utils.to_glb(
    output['gaussian'][0],
    output['mesh'][0],
    simplify=0.9,
    texture_size=1024
)
glb.export(os.path.join(args.output_dir, 'sample.glb'))

You may follow example.py for detailed hyper-parameters.

Gradio Demo

python app.py

📚 Citation

@inproceedings{yoon2026extend3d,
    title     = {Extend3D: Town-scale 3D Generation},
    author    = {Yoon, Seungwoo, and Kim, Jinmo, and Park, Jaesik},
    booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference},
    year      = {2026}
}

Acknowledgement

This repository is based on the implementation from Trellis. We sincerely thank the authors for releasing their code. We also thank the anonymous reviewers for their insightful and constructive feedback.