https://github.com/THU-luvision/GigaMVS

This repository is used for discussing issues regarding the **GigaMVS** dataset and benchmark. Please visit the following website for more details: http://gigamvs.com/
https://github.com/THU-luvision/GigaMVS

Last synced: 19 days ago
JSON representation

This repository is used for discussing issues regarding the **GigaMVS** dataset and benchmark. Please visit the following website for more details: http://gigamvs.com/

• Host: GitHub
• URL: https://github.com/THU-luvision/GigaMVS
• Owner: THU-luvision
• License: mit
• Created: 2022-02-12T13:20:39.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2022-02-12T13:21:38.000Z (over 2 years ago)
• Last Synced: 2024-02-26T23:36:57.335Z (4 months ago)
• Size: 1.95 KB
• Stars: 3
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Lists

• Awesome-Learning-MVS - GigaMVS

README

        
# GigaMVS: A Benchmark for Ultra-large-scale Gigapixel-level 3D Reconstruction[[Paper]](https://ieeexplore.ieee.org/document/9547729)[[Demo]()]

This repository is used for discussing issues regarding the **GigaMVS** dataset and benchmark. Please visit the following website for more details:

http://gigamvs.com/

## About

**GigaMVS** is the first gigapixel-image-based 3D reconstruction benchmark for ultra-large-scale scenes. The gigapixel images, with both wide field-of-view and high-resolution details, can clearly observe both the **Palace-scale** scene structure and **Relievo-scale** local details. Owing to the extremely large scale, complex occlusion, and gigapixel-level images, GigaMVS exposes problems that emerge from the poor scalability and efficiency of the existing MVS algorithms. We thoroughly investigate the state-of-the-art methods in terms of geometric and textural measurements, which point to the weakness of the existing methods and promising opportunities for future works. We believe that GigaMVS can benefit the community of 3D reconstruction and support the development of novel algorithms balancing robustness, scalability and accuracy.

## Citation

If you find this dataset useful for your research, please cite:

```

@ARTICLE{9547729,

  author={Zhang, Jianing and Zhang, Jinzhi and Mao, Shi and Ji, Mengqi and Wang, Guangyu and Chen, Zequn and Zhang, Tian and Yuan, Xiaoyun and Dai, Qionghai and Fang, Lu},

  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, 

  title={GigaMVS: A Benchmark for Ultra-large-scale Gigapixel-level 3D Reconstruction}, 

  year={2021},

  volume={},

  number={},

  pages={1-1},

  doi={10.1109/TPAMI.2021.3115028}}

```