DA-2K

# DA-2K Evaluation Benchmark

## Introduction


DA-2K is proposed in [Depth Anything V2](https://depth-anything-v2.github.io) to evaluate the relative depth estimation capability. It encompasses eight representative scenarios of `indoor`, `outdoor`, `non_real`, `transparent_reflective`, `adverse_style`, `aerial`, `underwater`, and `object`. It consists of 1K diverse high-quality images and 2K precise pair-wise relative depth annotations.

Please refer to our [paper](https://arxiv.org/abs/2406.09414) for details in constructing this benchmark.

## Usage

Please first [download the benchmark](https://huggingface.co/datasets/depth-anything/DA-2K/tree/main).

All annotations are stored in `annotations.json`. The annotation file is a JSON object where each key is the path to an image file, and the value is a list of annotations associated with that image. Each annotation describes two points and identifies which point is closer to the camera. The structure is detailed below:

```
{
"image_path": [
{
"point1": [h1, w1], # (vertical position, horizontal position)
"point2": [h2, w2], # (vertical position, horizontal position)
"closer_point": "point1" # we always set "point1" as the closer one
},
...
],
...
}
```

To visualize the annotations:
```bash
python visualize.py [--scene-type <type>]
```

**Options**
- `--scene-type <type>` (optional): Specify the scene type (`indoor`, `outdoor`, `non_real`, `transparent_reflective`, `adverse_style`, `aerial`, `underwater`, and `object`). Skip this argument or set <type> as `""` to include all scene types.

## Citation

If you find this benchmark useful, please consider citing:

```bibtex
@article{depth_anything_v2,
title={Depth Anything V2},
author={Yang, Lihe and Kang, Bingyi and Huang, Zilong and Zhao, Zhen and Xu, Xiaogang and Feng, Jiashi and Zhao, Hengshuang},
journal={arXiv:2406.09414},
year={2024}
}
```

# DA-2K 评测基准

## 简介

DA-2K由论文《Depth Anything V2》（https://depth-anything-v2.github.io）提出，旨在评估相对深度估计（relative depth estimation）能力。该基准涵盖8类典型场景：室内场景（indoor）、室外场景（outdoor）、非真实场景（non_real）、透明反射场景（transparent_reflective）、恶劣风格场景（adverse_style）、航拍场景（aerial）、水下场景（underwater）以及物体场景（object）。其包含1000张多样化的高质量图像，以及2000组精准的成对相对深度标注。

有关该基准构建的详细信息，请参阅我们的论文（https://arxiv.org/abs/2406.09414）。

## 使用方法
请首先[下载该基准数据集](https://huggingface.co/datasets/depth-anything/DA-2K/tree/main)。

所有标注均存储于`annotations.json`文件中。该标注文件为JSON对象，其中每个键对应一张图像文件的路径，值为与该图像关联的标注列表。每条标注描述两个点，并指明哪个点更靠近相机。其结构详述如下：

{
"image_path": [
{
"point1": [h1, w1], # （垂直坐标，水平坐标）
"point2": [h2, w2], # （垂直坐标，水平坐标）
"closer_point": "point1" # 我们默认将"point1"设为距离相机更近的点
},
...
],
...
}

若要可视化标注，可运行以下命令：
bash
python visualize.py [--scene-type <type>]

**可选参数**
- `--scene-type <type>`（可选）：指定场景类型（室内场景（indoor）、室外场景（outdoor）、非真实场景（non_real）、透明反射场景（transparent_reflective）、恶劣风格场景（adverse_style）、航拍场景（aerial）、水下场景（underwater）以及物体场景（object））。若跳过该参数或将<type>设为`""`，则包含所有场景类型。

## 引用
若您认为该基准数据集对您的研究有所帮助，请引用以下文献：
bibtex
@article{depth_anything_v2,
title={Depth Anything V2},
author={Yang, Lihe and Kang, Bingyi and Huang, Zilong and Zhao, Zhen and Xu, Xiaogang and Feng, Jiashi and Zhao, Hengshuang},
journal={arXiv:2406.09414},
year={2024}
}