yhsz123/Matterport3D_polished

---
license: other
license_name: matterport3d
license_link: LICENSE
dataset_info:
features:
- name: image
dtype: image
- name: caption
dtype: string
splits:
- name: train
num_bytes: 28034234867.423
num_examples: 10359
download_size: 28206967190
dataset_size: 28034234867.423
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---

# Matterport3D_polished

<a href='https://arxiv.org/abs/2510.11712'><img src='https://img.shields.io/badge/arXiv-Paper-red?logo=arxiv&logoColor=white' alt='arXiv'></a>
<a href='https://fenghora.github.io/DiT360-Page/'><img src='https://img.shields.io/badge/Project_Page-Website-green?logo=insta360&logoColor=white' alt='Project Page'></a>
<a href='https://huggingface.co/spaces/Insta360-Research/DiT360'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Live_Demo-blue'></a>


**Matterport3D_Polished** is a panoramic dataset derived from [Matterport3D](https://niessner.github.io/Matterport/), which was introduced in [DiT360](https://fenghora.github.io/DiT360-Page/).
This dataset contains 10,000+ high-resolution (2048 x 1024) indoor panoramic images along with corresponding prompts.
Compared with the original dataset, it removes the blurred artifacts at both ends, providing clearer and sharper visual details.

## Which tasks will benefit from our dataset?

- [x] Text-to-Panorama Generation

## ⚙️ Getting Started

This dataset is derived from the **Matterport3D** dataset, which is released under the Matterport [Dataset License Agreement](https://kaldir.vc.in.tum.de/matterport/MP_TOS.pdf).
A copy of the license is also available in our provided [LICENSE file](https://huggingface.co/datasets/Insta360-Research/Matterport3D_polished/blob/main/LICENSE.pdf).
Please review the Matterport3D license to ensure proper and compliant use of this dataset.

### Use with Datasets

For a quick use:

```python
from datasets import load_dataset

ds = load_dataset("Insta360-Research/Matterport3D_polished")

# check the data
print(ds["train"][0])
```

### Download the Dataset

To download the full dataset, you can use the following code.

```Bash
# Make sure you have git-lfs installed (https://git-lfs.com)
git lfs install
# When prompted for a password, use an access token with write permissions.
# Generate one from your settings: https://huggingface.co/settings/tokens
git clone https://huggingface.co/datasets/Insta360-Research/Matterport3D_polished
# If you want to clone without large files - just their pointers
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/datasets/Insta360-Research/Matterport3D_polished
```

If you encounter any issues, please refer to the official Hugging Face documentation.

## 🧷 Citation
```
@misc{dit360,
title={DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training},
author={Haoran Feng and Dizhe Zhang and Xiangtai Li and Bo Du and Lu Qi},
year={2025},
eprint={2510.11712},
archivePrefix={arXiv},
}
```
If you find our dataset useful, please also include a citation for Matterport3D:
```
@article{Matterport3D,
title={Matterport3D: Learning from RGB-D Data in Indoor Environments},
author={Chang, Angel and Dai, Angela and Funkhouser, Thomas and Halber, Maciej and Niessner, Matthias and Savva, Manolis and Song, Shuran and Zeng, Andy and Zhang, Yinda},
journal={International Conference on 3D Vision (3DV)},
year={2017}
}
```