{"url":"/dataset/matterport3d","name":"Matterport3D","full_name":null,"description_markdown":"The **Matterport3D** dataset is a large RGB-D dataset for scene understanding in indoor environments. It contains 10,800 panoramic views inside 90 real building-scale scenes, constructed from 194,400 RGB-D images. Each scene is a residential building consisting of multiple rooms and floor levels, and is annotated with surface construction, camera poses, and semantic segmentation.\r\n\r\nSource: [Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Intervention](https://arxiv.org/abs/1812.04155)","description_withheld":null,"homepage":"https://niessner.github.io/Matterport/","introduced_date":"2017-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/matterport3d-learning-from-rgb-d-data-in","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","first_author":"Angel Chang","url":null},"license":{"name":"Custom (non-commercial)","url":"http://kaldir.vc.in.tum.de/matterport/MP_TOS.pdf"},"modalities":[{"name":"3D","url":"/datasets/modality/3d"},{"name":"RGB-D","url":"/datasets/modality/rgb-d"}],"tasks":[{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"Depth Estimation","url":"/task/depth-estimation","datasets_with_task":"/datasets/task/depth-estimation"},{"name":"Monocular Depth Estimation","url":"/task/monocular-depth-estimation","datasets_with_task":"/datasets/task/monocular-depth-estimation"},{"name":"Depth Completion","url":"/task/depth-completion","datasets_with_task":"/datasets/task/depth-completion"},{"name":"Depth Prediction","url":"/task/depth-prediction","datasets_with_task":"/datasets/task/depth-prediction"}],"languages":[],"variants":["Matterport3D"],"data_loaders":[{"repo":"https://github.com/VAI3D/1","url":"https://github.com/VAI3D/1","frameworks":["pytorch"]}],"num_papers_in_archive":461,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/semantic-segmentation-on-matterport3d","task":"Semantic Segmentation","dataset_variant":"Matterport3D","rows":4,"metrics":["Test mIoU","Validation mIoU"],"first_row_in_archive_order":{"model":"SFSS-MMSI (RGB+Depth)","paper":"/paper/single-frame-semantic-segmentation-using","metrics":{"Test mIoU":"35.92","Validation mIoU":"39.19"},"code_links":[{"title":"sguttikon/SFSS-MMSI","url":"https://github.com/sguttikon/SFSS-MMSI"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/depth-completion-on-matterport3d","task":"Depth Completion","dataset_variant":"Matterport3D","rows":2,"metrics":["RMSE"],"first_row_in_archive_order":{"model":"DM-LRN-b4","paper":"/paper/decoder-modulation-for-indoor-depth","metrics":{"RMSE":"1.001"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/depth-estimation-on-matterport3d","task":"Depth Estimation","dataset_variant":"Matterport3D","rows":1,"metrics":["Abs Rel"],"first_row_in_archive_order":{"model":"UniFuse","paper":"/paper/unifuse-unidirectional-fusion-for-360-circ","metrics":{"Abs Rel":"0.1063"},"code_links":[{"title":"alibaba/UniFuse-Unidirectional-Fusion","url":"https://github.com/alibaba/UniFuse-Unidirectional-Fusion"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/monocular-depth-estimation-on-matterport3d","task":"Monocular Depth Estimation","dataset_variant":"Matterport3D","rows":1,"metrics":["Delta < 1.25","Delta < 1.25^2","Delta < 1.25^3","RMSE","absolute error","absolute relative error"],"first_row_in_archive_order":{"model":"NeWCRFs","paper":"/paper/new-crfs-neural-window-fully-connected-crfs-1","metrics":{"Delta < 1.25":"0.9376","Delta < 1.25^2":"0.9812","Delta < 1.25^3":"0.9933","RMSE":"0.4279","absolute error":"0.197","absolute relative error":"0.0793"},"code_links":[{"title":"aliyun/NeWCRFs","url":"https://github.com/aliyun/NeWCRFs"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/single-frame-semantic-segmentation-using","title":"Single Frame Semantic Segmentation Using Multi-Modal Spherical Images","date":"2023-08-18","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/new-crfs-neural-window-fully-connected-crfs-1","title":"NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation","date":"2022-03-03","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":5,"samples_unverified":5,"pointer_only_for_licence":10,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/unifuse-unidirectional-fusion-for-360-circ","title":"UniFuse: Unidirectional Fusion for 360$^{\\circ}$ Panorama Depth Estimation","date":"2021-02-06","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/decoder-modulation-for-indoor-depth","title":"Decoder Modulation for Indoor Depth Completion","date":"2020-05-18","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/indoor-depth-completion-with-boundary","title":"Indoor Depth Completion with Boundary Consistency and Self-Attention","date":"2019-08-22","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":13,"samples_ran":5,"samples_unverified":8,"pointer_only_for_licence":10,"papers_with_no_sample_that_ran":1,"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."}