{"url":"/dataset/wildplaces","name":"Wild-Places","full_name":null,"description_markdown":"Many existing datasets for lidar place recognition are solely representative of structured urban environments, and have recently been saturated in performance by deep learning based approaches. Natural and unstructured environments present many additional challenges for the tasks of long-term localisation but these environments are not represented in currently available datasets. \r\nTo address this we introduce Wild-Places, a challenging large-scale dataset for lidar place recognition in unstructured, natural environments.  Wild-Places contains eight lidar sequences collected with a handheld sensor payload over the course of fourteen months, containing a total of 63K undistorted lidar submaps along with accurate 6DoF ground truth.  This dataset contains multiple revisits both within and between sequences, allowing for both intra-sequence (i.e., loop closure detection) and inter-sequence (i.e., re-localisation) tasks.  We also benchmark several state-of-the-art approaches to demonstrate the challenges that this dataset introduces, particularly the case of long-term place recognition due to natural environments changing over time.  Our dataset and code is available at [https://csiro-robotics.github.io/Wild-Places](https://csiro-robotics.github.io/Wild-Places)","description_withheld":null,"homepage":"https://csiro-robotics.github.io/Wild-Places/","introduced_date":"2022-11-23","introduced_date_note":null,"introduced_by":{"paper":"/paper/wild-places-a-large-scale-dataset-for-lidar","title":"Wild-Places: A Large-Scale Dataset for Lidar Place Recognition in Unstructured Natural Environments","first_author":null,"url":null},"license":{"name":"Creative Commons Attribution Noncommercial-Share Alike 4.0 Licence","url":"https://creativecommons.org/licenses/by-nc-sa/4.0/"},"modalities":[{"name":"3D","url":"/datasets/modality/3d"},{"name":"LiDAR","url":"/datasets/modality/lidar"}],"tasks":[{"name":"Domain Adaptation","url":"/task/domain-adaptation","datasets_with_task":"/datasets/task/domain-adaptation"},{"name":"3D Place Recognition","url":"/task/3d-place-recognition","datasets_with_task":"/datasets/task/3d-place-recognition"},{"name":"Sequential Place Recognition","url":"/task/sequential-place-recognition","datasets_with_task":"/datasets/task/sequential-place-recognition"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Wild-Places"],"data_loaders":[{"repo":"https://github.com/csiro-robotics/Wild-Places","url":"https://github.com/csiro-robotics/Wild-Places","frameworks":["pytorch"]}],"num_papers_in_archive":18,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/3d-place-recognition-on-wild-places","task":"3D Place Recognition","dataset_variant":"Wild-Places","rows":4,"metrics":["AR@1 (Intra-Seq)","AR@1 Inter-Seq"],"first_row_in_archive_order":{"model":"ForestLPR","paper":"/paper/forestlpr-lidar-place-recognition-in-forests","metrics":{"AR@1 (Intra-Seq)":"77.62","AR@1 Inter-Seq":"78.73"},"code_links":[{"title":"shenyanqing1105/ForestLPR-CVPR2025","url":"https://github.com/shenyanqing1105/ForestLPR-CVPR2025"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/forestlpr-lidar-place-recognition-in-forests","title":"ForestLPR: LiDAR Place Recognition in Forests Attentioning Multiple BEV Density Images","date":"2025-03-06","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-point-cloud-based-place-recognition","title":"Improving Point Cloud Based Place Recognition with Ranking-based Loss and Large Batch Training","date":"2022-03-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/logg3d-net-locally-guided-global-descriptor","title":"LoGG3D-Net: Locally Guided Global Descriptor Learning for 3D Place Recognition","date":"2021-09-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/transloc3d-point-cloud-based-large-scale","title":"TransLoc3D : Point Cloud based Large-scale Place Recognition using Adaptive Receptive Fields","date":"2021-05-25","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"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."}