{"url":"/sota/omnnidirectional-stereo-depth-estimation-on","task":{"name":"Omnnidirectional Stereo Depth Estimation","url":"/task/omnnidirectional-stereo-depth-estimation","note":null},"dataset":{"name":"Helvipad","url":"/dataset/helvipad"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":null,"description_from":null,"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":["Depth-MAE","Depth-RMSE","Depth-MARE","Depth-LRCE","Disp-MAE","Disp-RMSE","Disp-MARE","Disp-LRCE"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Depth-MAE":"lower","Depth-RMSE":"lower","Depth-MARE":null,"Depth-LRCE":null,"Disp-MAE":"lower","Disp-RMSE":"lower","Disp-MARE":null,"Disp-LRCE":null}},"counts":{"rows":5,"rows_with_code":5,"rows_with_paper_page":5,"rows_dated":5,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"DFI-OmniStereo","metrics":{"Depth-LRCE":"0.397","Depth-MAE":"1.463","Depth-MARE":"0.108","Depth-RMSE":"3.767","Disp-LRCE":"0.058","Disp-MAE":"0.158","Disp-MARE":"0.120","Disp-RMSE":"0.338"},"uses_additional_data":false,"paper_date":"2025-03-30","paper":"/paper/boosting-omnidirectional-stereo-matching-with","paper_url":"https://arxiv.org/abs/2503.23502v1","paper_title":"Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation Model","code":"https://github.com/vita-epfl/DFI-OmniStereo","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"360-IGEV-Stereo","metrics":{"Depth-LRCE":"0.388","Depth-MAE":"1.720","Depth-MARE":"0.130","Depth-RMSE":"4.297","Disp-LRCE":"0.054","Disp-MAE":"0.188","Disp-MARE":"0.146","Disp-RMSE":"0.404"},"uses_additional_data":false,"paper_date":"2024-11-27","paper":"/paper/helvipad-a-real-world-dataset-for","paper_url":"https://arxiv.org/abs/2411.18335v2","paper_title":"Helvipad: A Real-World Dataset for Omnidirectional Stereo Depth Estimation","code":"https://github.com/vita-epfl/Helvipad","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"IGEV-Stereo","metrics":{"Depth-LRCE":"1.203","Depth-MAE":"1.860","Depth-MARE":"0.146","Depth-RMSE":"4.474","Disp-MAE":"0.225","Disp-MARE":"0.172","Disp-RMSE":"0.423"},"uses_additional_data":false,"paper_date":"2023-03-12","paper":"/paper/iterative-geometry-encoding-volume-for-stereo","paper_url":"https://arxiv.org/abs/2303.06615v2","paper_title":"Iterative Geometry Encoding Volume for Stereo Matching","code":"https://github.com/gangweix/igev","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"360SD-Net","metrics":{"Depth-LRCE":"0.904","Depth-MAE":"2.112","Depth-MARE":"0.152","Depth-RMSE":"5.077","Disp-MAE":"0.224","Disp-MARE":"0.191","Disp-RMSE":"0.419"},"uses_additional_data":false,"paper_date":"2019-11-11","paper":"/paper/360sd-net-360-stereo-depth-estimation-with","paper_url":"https://arxiv.org/abs/1911.04460v2","paper_title":"360SD-Net: 360° Stereo Depth Estimation with Learnable Cost Volume","code":"https://github.com/albert100121/360SD-Net","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":7,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"PSMNet","metrics":{"Depth-LRCE":"1.809","Depth-MAE":"2.509","Depth-MARE":"0.176","Depth-RMSE":"5.673","Disp-MAE":"0.286","Disp-MARE":"0.248","Disp-RMSE":"0.496"},"uses_additional_data":false,"paper_date":"2018-03-23","paper":"/paper/pyramid-stereo-matching-network","paper_url":"http://arxiv.org/abs/1803.08669v1","paper_title":"Pyramid Stereo Matching Network","code":"https://github.com/JiaRenChang/PSMNet","n_code_links":6,"syntology":{"n_ran":3,"n_unverified":8,"n_samples":11,"n_pointer_only_licence":0}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"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":2,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":6,"n_unverified":15,"n_samples":21,"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":6,"n_unverified":15,"n_samples":21,"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"}}}