Multi-exposure image stacks for testing HDR deghosting methods

This dataset contains a set of RAW and JPEG image stacks of multi-exposure image sequences that could be used for testing HDR reconstruction and deghosting methods. The unique feature of this dataset is that it contains both test image stacks, with motion and misalignment, and motion-free reference image stacks, which can be used with full-reference image quality metrics. In addition to that, we also provide the results of the subjective quality assessment experiment peformed on the set of merged HDR images. Please check the README.txt file for mode details.本数据集包含多曝光图像序列的RAW与JPEG图像栈，可用于测试高动态范围（High Dynamic Range，HDR）重建与去鬼影算法。本数据集的独特优势在于，同时涵盖存在运动与错位的测试图像栈，以及无运动的参考图像栈，可配合全参考图像质量评价指标开展相关实验。除此之外，本数据集还提供了针对融合所得HDR图像的主观质量评价实验结果。详细信息请参阅README.txt文件。

搜集汇总

背景与挑战

背景概述

该数据集提供多曝光图像堆栈，用于测试HDR重建和去鬼影方法，其独特之处在于同时包含有运动/未对齐的测试图像和无运动的参考图像，支持全参考质量评估。数据集还包括主观质量评估结果，采用开放访问许可，发布于2017年。