{"url":"/dataset/helvipad","name":"Helvipad","full_name":null,"description_markdown":"The Helvipad dataset is a real-world stereo dataset designed for omnidirectional depth estimation. It comprises 39,553 paired equirectangular images captured using a top-bottom 360° camera setup and corresponding pixel-wise depth and disparity labels derived from LiDAR point clouds.  The dataset spans diverse indoor and outdoor scenes under varying lighting conditions, including night-time environments.","description_withheld":null,"homepage":"https://vita-epfl.github.io/Helvipad/","introduced_date":"2024-11-27","introduced_date_note":null,"introduced_by":{"paper":"/paper/helvipad-a-real-world-dataset-for","title":"Helvipad: A Real-World Dataset for Omnidirectional Stereo Depth Estimation","first_author":"Mehdi Zayene","url":null},"license":{"name":"CC0","url":"https://github.com/vita-epfl/Helvipad?tab=CC0-1.0-1-ov-file"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Stereo Depth Estimation","url":"/task/stereo-depth-estimation","datasets_with_task":"/datasets/task/stereo-depth-estimation"},{"name":"Omnnidirectional Stereo Depth Estimation","url":"/task/omnnidirectional-stereo-depth-estimation","datasets_with_task":"/datasets/task/omnnidirectional-stereo-depth-estimation"},{"name":"Stereo Matching","url":"/task/stereo-matching-1","datasets_with_task":"/datasets/task/stereo-matching-1"}],"languages":[],"variants":["Helvipad"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/chcorbi/helvipad","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/omnnidirectional-stereo-depth-estimation-on","task":"Omnnidirectional Stereo Depth Estimation","dataset_variant":"Helvipad","rows":5,"metrics":["Depth-MAE","Depth-RMSE","Depth-MARE","Depth-LRCE","Disp-MAE","Disp-RMSE","Disp-MARE","Disp-LRCE"],"first_row_in_archive_order":{"model":"DFI-OmniStereo","paper":"/paper/boosting-omnidirectional-stereo-matching-with","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"},"code_links":[{"title":"vita-epfl/DFI-OmniStereo","url":"https://github.com/vita-epfl/DFI-OmniStereo"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/boosting-omnidirectional-stereo-matching-with","title":"Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation Model","date":"2025-03-30","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/helvipad-a-real-world-dataset-for","title":"Helvipad: A Real-World Dataset for Omnidirectional Stereo Depth Estimation","date":"2024-11-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/iterative-geometry-encoding-volume-for-stereo","title":"Iterative Geometry Encoding Volume for Stereo Matching","date":"2023-03-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/360sd-net-360-stereo-depth-estimation-with","title":"360SD-Net: 360° Stereo Depth Estimation with Learnable Cost Volume","date":"2019-11-11","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":3,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pyramid-stereo-matching-network","title":"Pyramid Stereo Matching Network","date":"2018-03-23","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":3,"samples_unverified":8,"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":21,"samples_ran":6,"samples_unverified":15,"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."}