MC-Blur
收藏资源简介:
MC-Blur数据集是由澳大利亚国立大学工程与计算机科学学院创建的一个大规模多原因图像去模糊基准数据集。该数据集包含多种模糊因素导致的模糊图像,如运动模糊、散焦模糊和真实世界模糊等。数据集通过高速相机捕捉的锐利图像平均化、超高清锐利图像与大尺寸核卷积、图像散焦处理以及多种相机模型捕捉的真实模糊图像等方式构建。MC-Blur数据集旨在为不同场景下的图像去模糊方法提供全面的性能评估,推动多原因图像去模糊的研究。
MC-Blur dataset is a large-scale multi-cause image deblurring benchmark dataset developed by the School of Engineering and Computer Science, Australian National University. This dataset contains blurred images induced by various blur factors, such as motion blur, defocus blur, and real-world blur. The dataset is constructed through multiple approaches: averaging sharp images captured by high-speed cameras, convolving ultra-high-definition sharp images with large-sized kernels, performing image defocus processing, and collecting real blurred images captured using diverse camera models. The MC-Blur dataset aims to provide comprehensive performance evaluation for image deblurring methods across different scenarios, and promote research on multi-cause image deblurring.




