{"url":"/dataset/make3d","name":"Make3D","full_name":null,"description_markdown":"The **Make3D** dataset is a monocular Depth Estimation dataset that contains 400 single training RGB and depth map pairs, and 134 test samples. The RGB images have high resolution, while the depth maps are provided at low resolution.\r\n\r\nSource: [Structured Coupled Generative Adversarial Networks for Unsupervised Monocular Depth Estimation](https://arxiv.org/abs/1908.05794)\r\nImage Source: [http://make3d.cs.cornell.edu/data.html#make3d](http://make3d.cs.cornell.edu/data.html#make3d)","description_withheld":null,"homepage":"http://make3d.cs.cornell.edu/data.html#make3d","introduced_date":"2009-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"Make3D: Learning 3D Scene Structure from a Single Still Image","first_author":null,"url":"https://doi.org/10.1109/TPAMI.2008.132"},"license":{"name":"CC BY-NC 3.0","url":"http://make3d.cs.cornell.edu/faq.html#:~:text=use%20of%20pictures%20on%20Make3d"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"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"}],"languages":[],"variants":["Make3D"],"data_loaders":[{"repo":"https://github.com/nianticlabs/monodepth2","url":"https://github.com/nianticlabs/monodepth2","frameworks":["pytorch"]}],"num_papers_in_archive":129,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/monocular-depth-estimation-on-make3d","task":"Monocular Depth Estimation","dataset_variant":"Make3D","rows":6,"metrics":["Abs Rel","RMSE","Sq Rel"],"first_row_in_archive_order":{"model":"SPIDepth","paper":"/paper/spidepth-strengthened-pose-information-for","metrics":{"Abs Rel":"0.299","RMSE":"6.672","Sq Rel":"1.931"},"code_links":[{"title":"Lavreniuk/SPIdepth","url":"https://github.com/Lavreniuk/SPIdepth"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/spidepth-strengthened-pose-information-for","title":"SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth Estimation","date":"2024-04-18","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":13,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/gcndepth-self-supervised-monocular-depth","title":"GCNDepth: Self-supervised Monocular Depth Estimation based on Graph Convolutional Network","date":"2021-12-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sharingan-combining-synthetic-and-real-data-1","title":"SharinGAN: Combining Synthetic and Real Data for Unsupervised Geometry Estimation","date":"2020-06-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-survey-on-deep-learning-techniques-for","title":"A Survey on Deep Learning Techniques for Stereo-based Depth Estimation","date":"2020-06-01","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/digging-into-self-supervised-monocular-depth","title":"Digging Into Self-Supervised Monocular Depth Estimation","date":"2018-06-04","rows_on_this_dataset":1,"code_links":15,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":24,"samples_ran":17,"samples_unverified":7,"pointer_only_for_licence":6,"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":38,"samples_ran":30,"samples_unverified":8,"pointer_only_for_licence":6,"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."}