百科.dev
全部条目在线工具AI 编程趋势榜开源项目技术资讯提交条目
登录
< 返回工具列表
G

Gen3DSR

> 编程语言
开源

Gen3DSR: 从单个视图中通过分而治之进行可推广的 3D 场景重构, 3DV2025

200 stars0 点赞2 次浏览
访问官网GitHub

工具介绍

Gen3DSR: 从单个视图中通过分而治之进行可推广的 3D 场景重构, 3DV2025

Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single View

This repository contains the official implementation of the 3DV2025 paper titled Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single View. Andreea Ardelean, Mert Özer, Bernhard Egger

News

21.03.2025: Evaluation code is released.

06.11.2024: Gen3DSR is accepted at 3DV2025!

15.07.2024: Inference code is released.

04.04.2024: Paper is available on .

Usage

  • Interactive scene reconstruction examples can be found on our project page.
  • A Dockerfile is provided for easy setup:
bash
docker build --build-arg HF_TOKEN= -t gen3dsr .
docker run -it --gpus all \
    --mount type=bind,source="$(pwd)/src",target=/app/src \
    --mount type=bind,source="$(pwd)/imgs",target=/app/imgs \
    --mount type=bind,source="$(pwd)/out",target=/app/out \
    gen3dsr python run.py --config ./configs/image.yaml
  • Alternatively, after following the detailed local installation instructions presented in INSTALL.md, the code can be run as follows:
bash
cd src
python run.py --config ./configs/image.yaml \
    scene.attributes.img_path='../imgs/demo_1.jpg' \
    scene.save_dir='../out/demo_1'
  • We recommend the user to check out the different inference options in image.yaml.
  • The reconstruction can be found in /reconstruction.
  • The code requires minimum 20GB of VRAM.

Evaluation

We provide here the information required to evaluate Gen3DSR on the subset of 100 scenes selected from the 3D-FRONT dataset as in our paper.

  • Downloading the data:
bash
cd imgs
git lfs install
git clone https://huggingface.co/datasets/andreead-a/FRONT3D
  • Running the method on a given scene:
bash
cd src
python run.py --config ./configs/front.yaml scene.attributes.render_task='5131' 
  • The reconstruction can be found in out/front3d/rec_
  • A script is provided to evaluate all reconstructed scenes against the ground truth:
bash
cd src
python eval_front.py --data_root ../imgs/FRONT3D --rec_path ../out/front3d
  • The results will be saved at out/front3d/metrics_full.json

Citation

@inproceedings{Ardelean2025Gen3DSR,
    title={Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single View},
    author={Ardelean, Andreea and Özer, Mert and Egger, Bernhard},
    booktitle = {International Conference on 3D Vision (3DV)},
    year={2025}
}

Acknowledgements

This work is built on many amazing research works and open-source projects, thanks a lot to all the authors for sharing!

  • DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation
  • High Quality Entity Segmentation
  • Perspective Fields for Single Image Camera Calibration
  • Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation
  • Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
  • Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image
  • OneFormer: One Transformer to Rule Universal Image Segmentation
  • One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization
  • Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively

This work was funded by the German Federal Ministry of Education and Research (BMBF), FKZ: 01IS22082 (IRRW). The authors are responsible for the content of this publication. The authors gratefully acknowledge the scientific support and HPC resources provided by the Erlangen National High Performance Computing Center (NHR@FAU) of the Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) under the NHR project b112dc IRRW. NHR funding is provided by federal and Bavarian state authorities. NHR@FAU hardware is partially funded by the German Research Foundation (DFG) – 440719683.

License

The code is released under the CC BY 4.0 LICENSE.

Issues· 3 开放

查看全部 Issues在 GitHub 打开

暂无开放 Issues,或尚未同步最近议题。

> 标签

Python

暂无评论,来聊聊你的看法吧

> 工具信息

发布日期2026年8月1日
最后更新2026年9月18日
分类编程语言
定价开源

> 相关工具

T
TypeScript
JavaScript 的超集,为前端与全栈提供静态类型
P
Python
通用编程语言,广泛用于 Web、数据与 AI
G
Go
Google 推出的简洁高效系统语言