|Description (include details on usage, files and paper references)||To encourage the open comparison of single image shadow removal in community, we provide an online benchmark site and a dataset. Our quantitatively verified high quality dataset contains a wide range of ground truth data (214 test cases in total). Each case is rated according to 4 attributes, which are texture, brokenness, colourfulness and softness, in 3 perceptual degrees from weak to strong.
The benchmark data and result can only be used with full reference to our paper:
Interactive Shadow Removal and Ground Truth for Variable Scene Categories
Han Gong and Darren Cosker, British Machine Vision Conference (BMVC), 2014
Interactive Removal and Ground Truth for Difficult Shadow Scenes
Han Gong and Darren Cosker, Journal of the Optical Society of America (JOSA) A, 2016
The benchmark can only be used for academic research or industrial research but cannot be used for commercial use.Images from the dataset may shown academic in research papers. However, images cannot be used for commercial or media purposes.