facebook/map-anything-benchmarking

---
license: apache-2.0
task_categories:
- image-to-3d
- depth-estimation
language:
- en
tags:
- computer-vision
- 3d-reconstruction
- multi-view-stereo
- depth-estimation
- camera-pose
- covisibility
- mapanything
- benchmarking
pretty_name: MapAnything Benchmarking Dataset
size_categories:
- 100B<n<1T
---

# MapAnything Benchmarking Dataset

## Dataset Description

This dataset contains the WAI format data used for benchmarking feed-forward 3D reconstruction models in the [MapAnything codebase](https://github.com/facebookresearch/map-anything).

Please see our [Data Processing README](https://github.com/facebookresearch/map-anything/data_processing/README.md) for more details.

## Citation

If you use this dataset in your research, please cite our paper:

```bibtex
@inproceedings{keetha2026mapanything,
title={{MapAnything}: Universal Feed-Forward Metric {3D} Reconstruction},
author={Nikhil Keetha and Norman M\"{u}ller and Johannes Sch\"{o}nberger and Lorenzo Porzi and Yuchen Zhang and Tobias Fischer and Arno Knapitsch and Duncan Zauss and Ethan Weber and Nelson Antunes and Jonathon Luiten and Manuel Lopez-Antequera and Samuel Rota Bul\`{o} and Christian Richardt and Deva Ramanan and Sebastian Scherer and Peter Kontschieder},
booktitle={International Conference on 3D Vision (3DV)},
year={2026},
organization={IEEE}
}
```

## License

The data is released under the [Apache 2.0 License](https://github.com/facebookresearch/map-anything/LICENSE).

## Links

- 🏠 **Project Page**: [https://map-anything.github.io](https://map-anything.github.io)
- 💻 **Code**: [GitHub Repository](https://github.com/facebookresearch/map-anything)

许可证：Apache-2.0
任务类别：
- 图像到3D（image-to-3d）
- 深度估计（depth-estimation）
语言：
- 英语
标签：
- 计算机视觉（computer-vision）
- 三维重建（3d-reconstruction）
- 多视图立体（multi-view-stereo）
- 深度估计（depth-estimation）
- 相机位姿（camera-pose）
- 共视性（covisibility）
- MapAnything
- 基准测试
易读名称：MapAnything基准测试数据集
规模类别：100B < n < 1T

# MapAnything基准测试数据集

## 数据集描述
本数据集包含用于在[MapAnything代码库](https://github.com/facebookresearch/map-anything)中基准测试前馈式三维重建模型的WAI格式数据。更多细节请参阅我们的[数据处理自述文档](https://github.com/facebookresearch/map-anything/data_processing/README.md)。

## 引用
若您在研究中使用本数据集，请引用如下论文：
bibtex
@inproceedings{keetha2026mapanything,
title={{MapAnything}: Universal Feed-Forward Metric {3D} Reconstruction},
author={Nikhil Keetha and Norman Müller and Johannes Schönberger and Lorenzo Porzi and Yuchen Zhang and Tobias Fischer and Arno Knapitsch and Duncan Zauss and Ethan Weber and Nelson Antunes and Jonathon Luiten and Manuel Lopez-Antequera and Samuel Rota Bulò and Christian Richardt and Deva Ramanan and Sebastian Scherer and Peter Kontschieder},
booktitle={International Conference on 3D Vision (3DV)},
year={2026},
organization={IEEE}
}

## 许可
本数据集遵循[Apache 2.0许可协议](https://github.com/facebookresearch/map-anything/LICENSE)发布。

## 相关链接
- 🏠 **项目主页**：[https://map-anything.github.io](https://map-anything.github.io)
- 💻 **代码仓库**：[GitHub仓库](https://github.com/facebookresearch/map-anything)