DOTmark v1.0

This benchmark for testing discrete optimal transport algorithms consists of 10 classes. Each class contains 10 images in each of the 5 different resolutions from 32×32 to 512×512 (in doubling steps per dimension). This allows for a total of 45 computations of Wasserstein distances between two images for any one class at any fixed resolution.<br><br>Classes 1–7 are random simulations based on various probability distributions. Images at different resolutions are generated independently from each other but according to the same laws. Classes 8–10 were obtained by ad-hoc choices of simple geometric shapes, classic test images and images of mitochondria acquired using STED super-resolution microscopy. For geometric shapes and classic test<br> images the various resolutions available are coarsenings of a single image. For the microscopy images different clippings of various sizes have been selected from larger images to obtain the various resolutions. <br>

本基准数据集用于测试离散最优传输（discrete optimal transport）算法，共包含10个类别。每个类别包含5种不同分辨率下的各10张图像，分辨率范围为32×32至512×512（每一维度按倍增步长递增）。在任意固定分辨率下，单个类别内任意两张图像间均可计算瓦瑟斯坦距离（Wasserstein distances），总计可完成45次此类计算。

类别1至7为基于多种概率分布生成的随机仿真样本。不同分辨率的图像彼此独立生成，但遵循相同的分布规则。类别8至10则通过自定义选取简单几何形状、经典测试图像，以及利用受激发射损耗超分辨率显微镜（STED super-resolution microscopy）采集的线粒体图像得到。对于几何形状与经典测试图像，其各可用分辨率均由单张图像降采样得到；对于显微镜图像，则通过从大尺寸原图中裁剪不同尺寸的区域，以获得对应分辨率的图像。

搜集汇总

背景与挑战

背景概述

DOTmark v1.0是一个用于测试离散最优传输算法的基准数据集，包含10个类别的图像，每个类别有10张不同分辨率的图像。图像来源包括随机模拟、几何形状、经典测试图像和显微镜图像，适用于算法性能的全面评估。