ai4ce/OCFBench

---
license: cc-by-nc-sa-4.0
language:
- en
pretty_name: OCFBench
size_categories:
- 10K<n<100K
---
# Dataset Card for OCFBench
[[Paper]](https://arxiv.org/abs/2310.11239)
[[Code]](https://github.com/ai4ce/Occ4cast/)
[[Website]](https://ai4ce.github.io/Occ4cast/)

<!-- Provide a quick summary of the dataset. -->

The OCFBench dataset is curated in the paper [**Occ4cast: LiDAR-based 4D Occupancy Completion and Forecasting**](https://arxiv.org/abs/2310.11239).
The dataset is processed from public autonomous driving data to support the training and evaluation of the novel **occupancy completion and forecasting (OCF)** task.

# Uses

Please download each `.sqf` file from individual directories and mount them to local system for usage.

For larger files that are splited into several parts, please run the following code to merge the parts before mounting:

```
cat output_prefix_* > merged.sqf
```

Please refer to our [GitHub repository](https://github.com/ai4ce/Occ4cast/) for dataset structure and loading details.

## Citation

<!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. -->

**BibTeX:**

```
@article{Liu2023occ4cast,
title={LiDAR-based 4D Occupancy Completion and Forecasting},
author={Xinhao Liu and Moonjun Gong and Qi Fang and Haoyu Xie and Yiming Li and Hang Zhao and Chen Feng},
journal={arXiv preprint arXiv:2310.11239},
year={2023}
}
```

原始信息汇总

数据集卡片 for OCFBench

概述

OCFBench 数据集是在论文 Occ4cast: LiDAR-based 4D Occupancy Completion and Forecasting 中精心策划的。该数据集从公开的自动驾驶数据中处理而来，旨在支持新颖的 occupancy completion and forecasting (OCF) 任务的训练和评估。

使用方法

请从各个目录下载每个 .sqf 文件，并将其挂载到本地系统以供使用。对于被拆分成多个部分的大型文件，请运行以下代码合并部分文件后再进行挂载：

bash cat output_prefix_* > merged.sqf

有关数据集结构和加载细节，请参考我们的 GitHub 仓库。

引用

BibTeX:

bibtex @article{Liu2023occ4cast, title={LiDAR-based 4D Occupancy Completion and Forecasting}, author={Xinhao Liu and Moonjun Gong and Qi Fang and Haoyu Xie and Yiming Li and Hang Zhao and Chen Feng}, journal={arXiv preprint arXiv:2310.11239}, year={2023} }