{"url":"/dataset/objectsroom","name":"ObjectsRoom","full_name":null,"description_markdown":"The **ObjectsRoom** dataset is based on the MuJoCo environment used by the Generative Query Network [4] and is a multi-object extension of the 3d-shapes dataset. The training set contains 1M scenes with up to three objects. We also provide ~1K test examples for the following variants:\r\n\r\n2.1 Empty room: scenes consist of the sky, walls, and floor only.\r\n\r\n2.2 Six objects: exactly 6 objects are visible in each image.\r\n\r\n2.3 Identical color: 4-6 objects are placed in the room and have an identical, randomly sampled color.\r\n\r\nDatapoints consist of an image and fixed number of masks. The first four masks correspond to the sky, floor, and two halves of the wall respectively. The remaining masks correspond to the foreground objects.\r\n\r\nSource: [Objects Room](https://github.com/deepmind/multi_object_datasets)","description_withheld":null,"homepage":"https://github.com/deepmind/multi_object_datasets","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Image Generation","url":"/task/image-generation","datasets_with_task":"/datasets/task/image-generation"},{"name":"Unsupervised Object Segmentation","url":"/task/unsupervised-object-segmentation","datasets_with_task":"/datasets/task/unsupervised-object-segmentation"}],"languages":[],"variants":["ObjectsRoom"],"data_loaders":[{"repo":"https://github.com/deepmind/multi_object_datasets","url":"https://github.com/deepmind/multi_object_datasets","frameworks":["tf"]},{"repo":"https://github.com/JohannesTheo/multi_object_datasets_torch","url":"https://github.com/JohannesTheo/multi_object_datasets_torch","frameworks":["pytorch"]}],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/unsupervised-object-segmentation-on-1","task":"Unsupervised Object Segmentation","dataset_variant":"ObjectsRoom","rows":5,"metrics":["ARI-FG"],"first_row_in_archive_order":{"model":"AST","paper":"/paper/unsupervised-multi-object-segmentation-using","metrics":{"ARI-FG":"0.87"},"code_links":[{"title":"BrunoSauvalle/AST","url":"https://github.com/BrunoSauvalle/AST"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-generation-on-objectsroom","task":"Image Generation","dataset_variant":"ObjectsRoom","rows":3,"metrics":["FID"],"first_row_in_archive_order":{"model":"GENESIS-V2","paper":"/paper/genesis-v2-inferring-unordered-object","metrics":{"FID":"52.6"},"code_links":[{"title":"applied-ai-lab/genesis","url":"https://github.com/applied-ai-lab/genesis"},{"title":"jinyangyuan/genesis","url":"https://github.com/jinyangyuan/genesis"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/unsupervised-multi-object-segmentation-using","title":"Unsupervised Multi-object Segmentation Using Attention and Soft-argmax","date":"2022-05-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/genesis-v2-inferring-unordered-object","title":"GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement","date":"2021-04-20","rows_on_this_dataset":7,"code_links":2,"syntology":null}],"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."}