{"url":"/dataset/gaze360","name":"Gaze360","full_name":"Physically Unconstrained Gaze Estimation in the Wild","description_markdown":"Understanding where people are looking is an informative social cue. In this work, we present Gaze360, a large-scale gaze-tracking dataset and method for robust 3D gaze estimation in unconstrained images. Our dataset consists of 238 subjects in indoor and outdoor environments with labelled 3D gaze across a wide range of head poses and distances. It is the largest publicly available dataset of its kind by both subject and variety, made possible by a simple and efficient collection method. Our proposed 3D gaze model extends existing models to include temporal information and to directly output an estimate of gaze uncertainty. We demonstrate the benefits of our model via an ablation study, and show its generalization performance via a cross-dataset evaluation against other recent gaze benchmark datasets. We furthermore propose a simple self-supervised approach to improve cross-dataset domain adaptation. Finally, we demonstrate an application of our model for estimating customer attention in a supermarket setting.\r\n\r\nImage source: [Gaze360: Physically Unconstrained Gaze Estimation in the Wild](https://arxiv.org/pdf/1910.10088v1.pdf)","description_withheld":null,"homepage":"http://gaze360.csail.mit.edu/","introduced_date":"2019-10-22","introduced_date_note":null,"introduced_by":{"paper":"/paper/gaze360-physically-unconstrained-gaze","title":"Gaze360: Physically Unconstrained Gaze Estimation in the Wild","first_author":"Petr Kellnhofer","url":null},"license":{"name":"Custom","url":"http://gaze360.csail.mit.edu/download.php"},"modalities":[],"tasks":[{"name":"Gaze Estimation","url":"/task/gaze-estimation","datasets_with_task":"/datasets/task/gaze-estimation"}],"languages":[],"variants":["Gaze360"],"data_loaders":[],"num_papers_in_archive":62,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/gaze-estimation-on-gaze360","task":"Gaze Estimation","dataset_variant":"Gaze360","rows":4,"metrics":["Angular Error"],"first_row_in_archive_order":{"model":"MCGaze","paper":"/paper/end-to-end-video-gaze-estimation-via","metrics":{"Angular Error":"10.02"},"code_links":[{"title":"zgchen33/mcgaze","url":"https://github.com/zgchen33/mcgaze"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/end-to-end-video-gaze-estimation-via","title":"End-to-end Video Gaze Estimation via Capturing Head-face-eye Spatial-temporal Interaction Context","date":"2023-10-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/l2cs-net-fine-grained-gaze-estimation-in","title":"L2CS-Net: Fine-Grained Gaze Estimation in Unconstrained Environments","date":"2022-03-07","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":5,"samples_unverified":5,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/weakly-supervised-physically-unconstrained","title":"Weakly-Supervised Physically Unconstrained Gaze Estimation","date":"2021-05-20","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/gaze360-physically-unconstrained-gaze","title":"Gaze360: Physically Unconstrained Gaze Estimation in the Wild","date":"2019-10-22","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":10,"samples_ran":5,"samples_unverified":5,"pointer_only_for_licence":2,"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."}