{"url":"/dataset/wildscenes","name":"WildScenes","full_name":null,"description_markdown":"WildScenes is a bi-modal benchmark dataset consisting of multiple large-scale, sequential traversals in natural environments, including semantic annotations in high-resolution 2D images and dense 3D LiDAR point clouds, and accurate 6-DoF pose information. The data is (1) trajectory-centric with accurate localization and globally aligned point clouds, (2) calibrated and synchronized to support bi-modal training and inference, and (3) containing different natural environments over 6 months to support research on domain adaptation. We introduce benchmarks on 2D and 3D semantic segmentation and evaluate a variety of recent deep-learning techniques to demonstrate the challenges in semantic segmentation in natural environments. We propose train-val-test splits for standard benchmarks as well as domain adaptation benchmarks and utilize an automated split generation technique to ensure the balance of class label distributions. The WildScenes benchmark webpage is https://csiro-robotics.github.io/WildScenes, and the data is publicly available at https://data.csiro.au/collection/csiro:61541 .","description_withheld":null,"homepage":"https://csiro-robotics.github.io/WildScenes/","introduced_date":"2023-12-23","introduced_date_note":null,"introduced_by":{"paper":"/paper/wildscenes-a-benchmark-for-2d-and-3d-semantic","title":"WildScenes: A Benchmark for 2D and 3D Semantic Segmentation in Large-scale Natural Environments","first_author":"Kavisha Vidanapathirana","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":"Images","url":"/datasets/modality/images"},{"name":"Point cloud","url":"/datasets/modality/point-cloud"},{"name":"LiDAR","url":"/datasets/modality/lidar"}],"tasks":[{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"2D Semantic Segmentation","url":"/task/2d-semantic-segmentation","datasets_with_task":"/datasets/task/2d-semantic-segmentation"},{"name":"3D Semantic Segmentation","url":"/task/3d-semantic-segmentation","datasets_with_task":"/datasets/task/3d-semantic-segmentation"},{"name":"Image Segmentation","url":"/task/image-segmentation","datasets_with_task":"/datasets/task/image-segmentation"},{"name":"LIDAR Semantic Segmentation","url":"/task/lidar-semantic-segmentation","datasets_with_task":"/datasets/task/lidar-semantic-segmentation"},{"name":"Semantic SLAM","url":"/task/semantic-slam","datasets_with_task":"/datasets/task/semantic-slam"},{"name":"Point Cloud Segmentation","url":"/task/point-cloud-segmentation","datasets_with_task":"/datasets/task/point-cloud-segmentation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["WildScenes"],"data_loaders":[{"repo":"https://github.com/csiro-robotics/WildScenes","url":"https://csiro-robotics.github.io/WildScenes/","frameworks":["pytorch"]}],"num_papers_in_archive":12,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/2d-semantic-segmentation-on-wildscenes","task":"2D Semantic Segmentation","dataset_variant":"WildScenes","rows":5,"metrics":["mIoU","mIoU (Temporal DA) ","mIoU (Env DA)"],"first_row_in_archive_order":{"model":"Mask2Former (Swin-L)","paper":"/paper/masked-attention-mask-transformer-for","metrics":{"mIoU":"47.85"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"facebookresearch/Mask2Former","url":"https://github.com/facebookresearch/Mask2Former"},{"title":"alibaba/EasyCV","url":"https://github.com/alibaba/EasyCV"},{"title":"DdeGeus/Mask2Former-IBS","url":"https://github.com/DdeGeus/Mask2Former-IBS"},{"title":"nihalsid/mask2former","url":"https://github.com/nihalsid/mask2former"},{"title":"MindSpore-scientific/code-7","url":"https://github.com/MindSpore-scientific/code-7/tree/main/Mask2Former"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/3d-semantic-segmentation-on-wildscenes","task":"3D Semantic Segmentation","dataset_variant":"WildScenes","rows":4,"metrics":["mIoU","mIoU (Temporal DA)","mIoU (Env DA)"],"first_row_in_archive_order":{"model":"Cylinder3D","paper":"/paper/cylinder3d-an-effective-3d-framework-for","metrics":{"mIoU":"40.07"},"code_links":[{"title":"xinge008/Cylinder3D","url":"https://github.com/xinge008/Cylinder3D"},{"title":"hongfz16/DS-Net","url":"https://github.com/hongfz16/DS-Net"},{"title":"L-Reichardt/Cylinder3D-updated-CUDA","url":"https://github.com/L-Reichardt/Cylinder3D-updated-CUDA"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/spherical-transformer-for-lidar-based-3d","title":"Spherical Transformer for LiDAR-based 3D Recognition","date":"2023-03-22","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":4,"samples_unverified":9,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/masked-attention-mask-transformer-for","title":"Masked-attention Mask Transformer for Universal Image Segmentation","date":"2021-12-02","rows_on_this_dataset":2,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":2,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/segformer-simple-and-efficient-design-for","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","date":"2021-05-31","rows_on_this_dataset":1,"code_links":28,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":86,"samples_ran":48,"samples_unverified":38,"pointer_only_for_licence":15,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/cylinder3d-an-effective-3d-framework-for","title":"Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation","date":"2020-08-04","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/searching-efficient-3d-architectures-with","title":"Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution","date":"2020-07-31","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/4d-spatio-temporal-convnets-minkowski","title":"4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks","date":"2019-04-18","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/unified-perceptual-parsing-for-scene","title":"Unified Perceptual Parsing for Scene Understanding","date":"2018-07-26","rows_on_this_dataset":1,"code_links":25,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":28,"samples_ran":9,"samples_unverified":19,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rethinking-atrous-convolution-for-semantic","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","date":"2017-06-17","rows_on_this_dataset":1,"code_links":77,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":3,"samples_unverified":4,"pointer_only_for_licence":3,"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":7,"samples_harvested":147,"samples_ran":67,"samples_unverified":80,"pointer_only_for_licence":20,"papers_with_no_sample_that_ran":1,"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."}