The MIT-Adobe FiveK dataset consists of 5,000 photographs taken with SLR cameras by a set of different photographers. They are all in RAW format; that is, all the information recorded by the camera sensor is preserved. We made sure that these photographs cover a broad range of scenes, subjects, and lighting conditions. We then hired five photography students in an art school to adjust the tone of the photos. Each of them retouched all the 5,000 photos using a software dedicated to photo adjustment (Adobe Lightroom) on which they were extensively trained. We asked the retouchers to achieve visually pleasing renditions, akin to a postcard. The retouchers were compensated for their work. This dataset was collected for our project on learning photographic adjustments. When using images from this dataset, please cite this dataset using the following BibTeX: @inproceedings{fivek, author = "Vladimir Bychkovsky and Sylvain Paris and Eric Chan and Fr{\'e}do Durand", title = "Learning Photographic Global Tonal Adjustment with a Database of Input / Output Image Pairs", booktitle = "The Twenty-Fourth IEEE Conference on Computer Vision and Pattern Recognition", year = "2011" } Source: https://data.csail.mit.edu/graphics/fivek/ Image source: https://data.csail.mit.edu/graphics/fivek/
This newly curated synthetic dataset specifies an additional reference region to guide image harmonization. There are 118,287 training images and 959 test images. The dataset consists of objects, backgrounds, and people. IntHarmony has the following information for each data instance: composite image, ground truth, foreground mask of the composite foreground, and a guide mask that provides information about the reference region to guide harmonization. IntHarmony is built on top of the MS-COCO dataset, and makes use of the instance masks provided in MS-COCO to simulate foreground and reference regions. First, a random instance mask is selected to pick the foreground region. The selected foreground region is then augmented using a wide set of meaningful augmentations focusing on luminance, contrast and color. Another random instance mask is used to get the reference guide mask. The original image is considered the ground truth. The instance masks and the augmentations are chosen at random to induce more generalizability to the network.