https://github.com/aim-uofa/geobench
A toolbox for benchmarking SOTA discriminative and generative geometry estimation models.
https://github.com/aim-uofa/geobench
benchmark monocular-depth-estimation monocular-surface-normal-estimation
Last synced: 10 months ago
JSON representation
A toolbox for benchmarking SOTA discriminative and generative geometry estimation models.
- Host: GitHub
- URL: https://github.com/aim-uofa/geobench
- Owner: aim-uofa
- License: bsd-2-clause
- Created: 2024-06-16T09:36:10.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2024-08-29T06:54:45.000Z (almost 2 years ago)
- Last Synced: 2025-04-07T20:50:07.395Z (about 1 year ago)
- Topics: benchmark, monocular-depth-estimation, monocular-surface-normal-estimation
- Language: Python
- Homepage:
- Size: 904 KB
- Stars: 61
- Watchers: 11
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# ⚡ GeoBench: 3D Geometry Estimation Made Easy
🔰 [Project Page](https://yongtaoge.github.io/projects/geobench/), 📑 [Paper](https://arxiv.org/abs/2406.12671)
[Yongtao Ge]()1,2, [Guangkai Xu]()1, [Zhiyue Zhao]()1, [Libo Sun]()2, [Zheng Huang]()1, [Yanlong Sun]()3, [Hao Chen]()1, [Chunhua Shen]()1
1[Zhejiang University](https://www.zju.edu.cn/english/),
2[The University of Adelaide](https://www.adelaide.edu.au/aiml/),
3[Tsinghua University](https://www.tsinghua.edu.cn/en/)
> This toolbox streamlines the use and evaluation for state-of-the-art discriminative and generative geometry estimation models, which can be served as foundation models for various downstream 3D reconstruction applications, including:
- [x] [Metric3D-V2](https://arxiv.org/abs/2404.15506)
- [ ] [UniDepth](https://arxiv.org/abs/2403.18913)
- [x] [Depth-Anything-V2](https://arxiv.org/abs/2406.09414)
- [x] [Depth-Anything](https://arxiv.org/abs/2401.10891)
- [x] [DSINE](https://arxiv.org/abs/2403.00712)
- [x] [Marigold](https://arxiv.org/abs/2312.02145)
- [x] [DMP](https://arxiv.org/abs/2311.18832)
- [x] [Genpercept](https://arxiv.org/abs/2403.06090)
- [x] [Geowizard](https://arxiv.org/abs/2403.12013)
- [x] [DepthFM](https://arxiv.org/abs/2403.13788)
## Install
```
pip install -r requirements.txt
pip install -e . -v
```
## Inference Demos
```
# inference Marigold
sh scripts/run_marigold.sh
# inference Metric3D
sh scripts/run_metric3d.sh
# inference Depth-Anything
sh scripts/run_depthanything.sh
# inference GenPercept
sh scripts/run_genpercept.sh
# inference DSINE
sh scripts/run_dsine.sh
```
## Benchmarks and Model Zoo
Stay tuned, comming soon.
## License
For non-commercial academic use, this project is licensed under [the 2-clause BSD License](https://opensource.org/license/bsd-2-clause).
For commercial use, please contact [Chunhua Shen](mailto:chhshen@gmail.com).
Note that any third-party software/library involved in this project is licensed under its own license.
## Citation
If you find the toolbox useful for your project, please cite our paper:
```
@article{ge2024geobench,
title={GeoBench: Benchmarking and Analyzing Monocular Geometry Estimation Models},
author={Ge, Yongtao and Xu, Guangkai, and Zhao, Zhiyue and Huang, zheng and Sun, libo and Sun, Yanlong and Chen, Hao and Shen, Chunhua},
journal={arXiv preprint arXiv:2406.12671},
year={2024}
}
```