{"url":"/dataset/4d-or","name":"4D-OR","full_name":null,"description_markdown":"4D-OR includes a total of 6734 scenes, recorded by six calibrated RGB-D Kinect sensors 1 mounted to the ceiling of the OR, with one frame-per-second, providing synchronized RGB and depth images. We provide fused point cloud sequences of entire scenes, automatically annotated human 6D poses and 3D bounding boxes for OR objects. Furthermore, we provide SSG annotations for each step of the surgery together with the clinical roles of all the humans in the scenes, e.g., nurse, head surgeon, anesthesiologist.","description_withheld":null,"homepage":"https://github.com/egeozsoy/4D-OR","introduced_date":"2022-03-22","introduced_date_note":null,"introduced_by":{"paper":"/paper/4d-or-semantic-scene-graphs-for-or-domain","title":"4D-OR: Semantic Scene Graphs for OR Domain Modeling","first_author":"Ege Özsoy","url":null},"license":{"name":"CC-BY-NC","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Graphs","url":"/datasets/modality/graphs"},{"name":"3D","url":"/datasets/modality/3d"},{"name":"Point cloud","url":"/datasets/modality/point-cloud"},{"name":"Medical","url":"/datasets/modality/medical"},{"name":"Time series","url":"/datasets/modality/time-series"},{"name":"RGB-D","url":"/datasets/modality/rgb-d"},{"name":"RGB Video","url":"/datasets/modality/rgb-video"}],"tasks":[{"name":"3D Object Detection","url":"/task/3d-object-detection","datasets_with_task":"/datasets/task/3d-object-detection"},{"name":"3D Human Pose Estimation","url":"/task/3d-human-pose-estimation","datasets_with_task":"/datasets/task/3d-human-pose-estimation"},{"name":"Panoptic Segmentation","url":"/task/panoptic-segmentation","datasets_with_task":"/datasets/task/panoptic-segmentation"},{"name":"2D Panoptic Segmentation","url":"/task/2d-panoptic-segmentation","datasets_with_task":"/datasets/task/2d-panoptic-segmentation"},{"name":"Scene Graph Generation","url":"/task/scene-graph-generation","datasets_with_task":"/datasets/task/scene-graph-generation"},{"name":"Video Panoptic Segmentation","url":"/task/video-panoptic-segmentation","datasets_with_task":"/datasets/task/video-panoptic-segmentation"},{"name":"4D Panoptic Segmentation","url":"/task/4d-panoptic-segmentation","datasets_with_task":"/datasets/task/4d-panoptic-segmentation"},{"name":"3D Panoptic Segmentation","url":"/task/3d-panoptic-segmentation","datasets_with_task":"/datasets/task/3d-panoptic-segmentation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["4D-OR"],"data_loaders":[],"num_papers_in_archive":11,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/scene-graph-generation-on-4d-or","task":"Scene Graph Generation","dataset_variant":"4D-OR","rows":5,"metrics":["F1"],"first_row_in_archive_order":{"model":"ORacle","paper":"/paper/oracle-large-vision-language-models-for","metrics":{"F1":"0.91"},"code_links":[{"title":"egeozsoy/Oracle","url":"https://github.com/egeozsoy/Oracle"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-panoptic-segmentation-on-4d-or","task":"Video Panoptic Segmentation","dataset_variant":"4D-OR","rows":2,"metrics":["VPQ"],"first_row_in_archive_order":{"model":"MM-OR-VPQ4","paper":"/paper/mm-or-a-large-multimodal-operating-room","metrics":{"VPQ":"69.8"},"code_links":[{"title":"egeozsoy/MM-OR","url":"https://github.com/egeozsoy/MM-OR"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/2d-panoptic-segmentation-on-4d-or","task":"2D Panoptic Segmentation","dataset_variant":"4D-OR","rows":1,"metrics":["VPQ"],"first_row_in_archive_order":{"model":"MM-OR","paper":"/paper/mm-or-a-large-multimodal-operating-room","metrics":{"VPQ":"71.8"},"code_links":[{"title":"egeozsoy/MM-OR","url":"https://github.com/egeozsoy/MM-OR"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/mm-or-a-large-multimodal-operating-room","title":"MM-OR: A Large Multimodal Operating Room Dataset for Semantic Understanding of High-Intensity Surgical Environments","date":"2025-03-04","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/oracle-large-vision-language-models-for","title":"ORacle: Large Vision-Language Models for Knowledge-Guided Holistic OR Domain Modeling","date":"2024-04-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/labrad-or-lightweight-memory-scene-graphs-for","title":"LABRAD-OR: Lightweight Memory Scene Graphs for Accurate Bimodal Reasoning in Dynamic Operating Rooms","date":"2023-03-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/location-free-scene-graph-generation","title":"Location-Free Scene Graph Generation","date":"2023-03-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/4d-or-semantic-scene-graphs-for-or-domain","title":"4D-OR: Semantic Scene Graphs for OR Domain Modeling","date":"2022-03-22","rows_on_this_dataset":1,"code_links":1,"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."}