{"url":"/dataset/intharmony","name":"IntHarmony","full_name":null,"description_markdown":"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.\r\n\r\nIntHarmony 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. \r\n\r\nIntHarmony 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.","description_withheld":null,"homepage":"https://jeya-maria-jose.github.io/IPH-web/","introduced_date":"2022-03-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/interactive-portrait-harmonization","title":"Interactive Portrait Harmonization","first_author":"Jeya Maria Jose Valanarasu","url":null},"license":{"name":"MIT License","url":"https://github.com/jeya-maria-jose/Interactive-Portrait-Harmonization/blob/main/LICENSE"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Photo Retouching","url":"/task/photo-retouching","datasets_with_task":"/datasets/task/photo-retouching"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["IntHarmony"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}