{"url":"/sota/depth-estimation-on-stanford2d3d-panoramic","task":{"name":"Depth Estimation","url":"/task/depth-estimation","note":null},"dataset":{"name":"Stanford2D3D Panoramic","url":"/dataset/2d-3d-s"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Depth Estimation** is the task of measuring the distance of each pixel relative to the camera. Depth is extracted from either monocular (single) or stereo (multiple views of a scene) images. Traditional methods use multi-view geometry to find the relationship between the images. Newer methods can directly estimate depth by minimizing the regression loss, or by learning to generate a novel view from a sequence. The most popular benchmarks are KITTI and NYUv2. Models are typically evaluated according to a RMS metric.\r\n\r\n<span class=\"description-source\">Source: [DIODE: A Dense Indoor and Outdoor DEpth Dataset ](https://arxiv.org/abs/1908.00463)</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["RMSE","absolute relative error"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"RMSE":"lower","absolute relative error":"lower"}},"counts":{"rows":18,"rows_with_code":12,"rows_with_paper_page":18,"rows_dated":18,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"HiMODE","metrics":{"RMSE":"0.2619","absolute relative error":"0.0532"},"uses_additional_data":false,"paper_date":"2022-04-11","paper":"/paper/himode-a-hybrid-monocular-omnidirectional","paper_url":"https://arxiv.org/abs/2204.05007v1","paper_title":"HiMODE: A Hybrid Monocular Omnidirectional Depth Estimation Model","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"FreDSNet","metrics":{"RMSE":"0.2727","absolute relative error":"0.0952"},"uses_additional_data":false,"paper_date":"2022-10-04","paper":"/paper/fredsnet-joint-monocular-depth-and-semantic","paper_url":"https://arxiv.org/abs/2210.01595v2","paper_title":"FreDSNet: Joint Monocular Depth and Semantic Segmentation with Fast Fourier Convolutions","code":"https://github.com/sbrunoberenguel/fredsnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"NLFB","metrics":{"RMSE":"0.2776","absolute relative error":"0.0649"},"uses_additional_data":false,"paper_date":"2021-09-22","paper":"/paper/improving-360-monocular-depth-estimation-via","paper_url":"https://arxiv.org/abs/2109.10563v3","paper_title":"Improving 360 Monocular Depth Estimation via Non-local Dense Prediction Transformer and Joint Supervised and Self-supervised Learning","code":"https://github.com/yuniw18/Joint_360depth","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"PanoFormer","metrics":{"RMSE":"0.3083","absolute relative error":"0.0405"},"uses_additional_data":false,"paper_date":"2022-03-17","paper":"/paper/panoformer-panorama-transformer-for-indoor","paper_url":"https://arxiv.org/abs/2203.09283v2","paper_title":"PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation","code":"https://github.com/zhijieshen-bjtu/panoformer","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"ACDNet","metrics":{"RMSE":"0.341","absolute relative error":"0.0984"},"uses_additional_data":false,"paper_date":"2021-12-29","paper":"/paper/acdnet-adaptively-combined-dilated","paper_url":"https://arxiv.org/abs/2112.14440v2","paper_title":"ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth Estimation","code":"https://github.com/zcq15/acdnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"OmniFusion (2-iter)","metrics":{"RMSE":"0.3474","absolute relative error":"0.095"},"uses_additional_data":false,"paper_date":"2022-03-02","paper":"/paper/omnifusion-360-monocular-depth-estimation-via","paper_url":"https://arxiv.org/abs/2203.00838v2","paper_title":"OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion","code":"https://github.com/yuyanli0831/omnifusion","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":2,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"GLPanoDepth","metrics":{"RMSE":"0.3493"},"uses_additional_data":false,"paper_date":"2022-02-06","paper":"/paper/glpanodepth-global-to-local-panoramic-depth","paper_url":"https://arxiv.org/abs/2202.02796v2","paper_title":"GLPanoDepth: Global-to-Local Panoramic Depth Estimation","code":"https://github.com/LeoDarcy/GLPanoDepth","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"Neural Contourlet Network","metrics":{"RMSE":"0.3528","absolute relative error":"0.0558"},"uses_additional_data":false,"paper_date":"2022-08-03","paper":"/paper/neural-contourlet-network-for-monocular-360","paper_url":"https://arxiv.org/abs/2208.01817v1","paper_title":"Neural Contourlet Network for Monocular 360 Depth Estimation","code":"https://github.com/zhijieshen-bjtu/neural-contourlet-network-for-mode","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"SliceNet","metrics":{"RMSE":"0.3684","absolute relative error":"0.0744"},"uses_additional_data":false,"paper_date":"2021-06-19","paper":"/paper/slicenet-deep-dense-depth-estimation-from-a","paper_url":"http://openaccess.thecvf.com//content/CVPR2021/html/Pintore_SliceNet_Deep_Dense_Depth_Estimation_From_a_Single_Indoor_Panorama_CVPR_2021_paper.html","paper_title":"SliceNet: Deep Dense Depth Estimation From a Single Indoor Panorama Using a Slice-Based Representation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"DisConv","metrics":{"RMSE":"0.369","absolute relative error":"0.176"},"uses_additional_data":false,"paper_date":"2018-09-01","paper":"/paper/distortion-aware-convolutional-filters-for","paper_url":"http://openaccess.thecvf.com/content_ECCV_2018/html/Keisuke_Tateno_Distortion-Aware_Convolutional_Filters_ECCV_2018_paper.html","paper_title":"Distortion-Aware Convolutional Filters for Dense Prediction in Panoramic Images","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"UniFuse with fusion","metrics":{"RMSE":"0.3691","absolute relative error":"0.1114"},"uses_additional_data":false,"paper_date":"2021-02-06","paper":"/paper/unifuse-unidirectional-fusion-for-360-circ","paper_url":"https://arxiv.org/abs/2102.03550v2","paper_title":"UniFuse: Unidirectional Fusion for 360$^{\\circ}$ Panorama Depth Estimation","code":"https://github.com/alibaba/UniFuse-Unidirectional-Fusion","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"BiFuse++","metrics":{"RMSE":"0.372","absolute relative error":"0.1117"},"uses_additional_data":false,"paper_date":"2022-09-07","paper":"/paper/bifuse-self-supervised-and-efficient-bi","paper_url":"https://arxiv.org/abs/2209.02952v1","paper_title":"BiFuse++: Self-supervised and Efficient Bi-projection Fusion for 360 Depth Estimation","code":"https://github.com/fuenwang/bifusev2","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":12,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"PanoDepth","metrics":{"RMSE":"0.3747","absolute relative error":"0.0972"},"uses_additional_data":false,"paper_date":"2022-02-02","paper":"/paper/panodepth-a-two-stage-approach-for-monocular","paper_url":"https://arxiv.org/abs/2202.01323v1","paper_title":"PanoDepth: A Two-Stage Approach for Monocular Omnidirectional Depth Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"HoHoNet (ResNet-101)","metrics":{"RMSE":"0.3834","absolute relative error":"0.1014"},"uses_additional_data":false,"paper_date":"2020-11-23","paper":"/paper/hohonet-360-indoor-holistic-understanding","paper_url":"https://arxiv.org/abs/2011.11498v3","paper_title":"HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Features","code":"https://github.com/sunset1995/HoHoNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"BiFuse with fusion","metrics":{"RMSE":"0.4142","absolute relative error":"0.1209"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/bifuse-monocular-360-depth-estimation-via-bi","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Wang_BiFuse_Monocular_360_Depth_Estimation_via_Bi-Projection_Fusion_CVPR_2020_paper.html","paper_title":"BiFuse: Monocular 360 Depth Estimation via Bi-Projection Fusion","code":"https://github.com/Yeh-yu-hsuan/BiFuse","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"Jin et al.","metrics":{"RMSE":"0.421"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/geometric-structure-based-and-regularized","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Jin_Geometric_Structure_Based_and_Regularized_Depth_Estimation_From_360_Indoor_CVPR_2020_paper.html","paper_title":"Geometric Structure Based and Regularized Depth Estimation From 360 Indoor Imagery","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":17,"model":"SphereDepth","metrics":{"RMSE":"0.4512","absolute relative error":"0.1158"},"uses_additional_data":false,"paper_date":"2022-08-29","paper":"/paper/spheredepth-panorama-depth-estimation-from","paper_url":"https://arxiv.org/abs/2208.13714v3","paper_title":"SphereDepth: Panorama Depth Estimation from Spherical Domain","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":18,"model":"OmniDepth","metrics":{"RMSE":"0.6152","absolute relative error":"0.1996 "},"uses_additional_data":false,"paper_date":"2018-07-25","paper":"/paper/omnidepth-dense-depth-estimation-for-indoors","paper_url":"http://arxiv.org/abs/1807.09620v1","paper_title":"OmniDepth: Dense Depth Estimation for Indoors Spherical Panoramas","code":"https://github.com/VCL3D/SphericalViewSynthesis","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":5,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":5,"distinct_papers_with_any_sample_ran":4,"samples_over_distinct_papers":{"n_ran":10,"n_unverified":26,"n_samples":36,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":10,"n_unverified":26,"n_samples":36,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}