haotongl/SceneNetRGBD

---
license: other
license_name: scenenet-rgbd-original
license_link: https://robotvault.bitbucket.io/scenenet-rgbd.html
tags:
- depth-estimation
- scene-understanding
- rgb-d
- synthetic
pretty_name: SceneNetRGBD
---

# SceneNetRGBD

This is a mirror of the **SceneNetRGBD** dataset. The original download links at [https://robotvault.bitbucket.io/scenenet-rgbd.html](https://robotvault.bitbucket.io/scenenet-rgbd.html) are no longer available, so this copy is provided here for research convenience.

## Files

| File | Description |
|------|-------------|
| `SceneNetRGBD-val.tar.gz` | Validation set (~15 GB) |
| `train_0.tar.gz` – `train_16.tar.gz` | Training set split into 17 shards (~16 GB each, ~277 GB total) |

## Citation

If you use this dataset, please cite the original paper:

```bibtex
@inproceedings{mccormac2017scenenet,
title={SceneNet RGB-D: Can 5M Synthetic Images Beat Generic ImageNet Pre-training on Indoor Segmentation?},
author={McCormac, John and Handa, Ankur and Leutenegger, Stefan and Davison, Andrew J},
booktitle={Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
year={2017}
}
```

## Disclaimer

**All copyrights belong to the original authors.** This repository is an unofficial mirror created solely because the original download links are no longer functional. This dataset is redistributed for academic and research purposes only. If you are an original author and would like this mirror removed, please open an issue.