{"url":"/dataset/cam2bev","name":"Cam2BEV","full_name":null,"description_markdown":"The [dataset](https://gitlab.ika.rwth-aachen.de/cam2bev/cam2bev-data) contains two subsets of synthetic, semantically segmented road-scene images, which have been created for developing and applying the methodology described in the paper **\"A Sim2Real Deep Learning Approach for the Transformation of Images from Multiple Vehicle-Mounted Cameras to a Semantically Segmented Image in Bird’s Eye View\"** ([IEEE Xplore](https://ieeexplore.ieee.org/document/9294462), [arXiv](http://arxiv.org/abs/2005.04078), [YouTube](https://www.youtube.com/watch?v=TzXuwt56a0E))\r\n\r\nThe dataset can be used through the official code implementation of the Cam2BEV methodology described on [Github](https://github.com/ika-rwth-aachen/Cam2BEV).\r\n\r\n\r\n| Dataset | # Training Samples | # Validation Samples | # Vehicle Cameras | # Semantic Classes | Contained Images (examples) |\r\n| --- | --- | --- | --- | --- | --- |\r\n| [Dataset 1](https://gitlab.ika.rwth-aachen.de/cam2bev/cam2bev-data/-/tree/master/2_F): 360° Surround | 33199 | 3731 | 4 (front, rear, left, right) | 30 (CityScapes) | [front camera](https://gitlab.ika.rwth-aachen.de/cam2bev/cam2bev-data/-/raw/master/1_FRLR/examples/front.png), [rear camera](https://gitlab.ika.rwth-aachen.de/cam2bev/cam2bev-data/-/raw/master/1_FRLR/examples/rear.png), [left camera](https://gitlab.ika.rwth-aachen.de/cam2bev/cam2bev-data/-/raw/master/1_FRLR/examples/left.png), [right camera](https://gitlab.ika.rwth-aachen.de/cam2bev/cam2bev-data/-/raw/master/1_FRLR/examples/right.png), [bird's eye view](https://gitlab.ika.rwth-aachen.de/cam2bev/cam2bev-data/-/raw/master/1_FRLR/examples/bev.png), [bird's eye view incl. occlusion](https://gitlab.ika.rwth-aachen.de/cam2bev/cam2bev-data/-/raw/master/1_FRLR/examples bev+occlusion.png), [homography view](https://gitlab.ika.rwth-aachen.de/cam2bev/cam2bev-data/-/raw/master/1_FRLR/examples/homography.png) |\r\n| [Dataset 2](https://gitlab.ika.rwth-aachen.de/cam2bev/cam2bev-data/-/tree/master/2_F): Front Camera only | 32246 | 3172 | 1 (front) | 30 (CityScapes) | [front camera](https://gitlab.ika.rwth-aachen.de/cam2bev/cam2bev-data/-/raw/master/2_F/examples/front.png), [bird's eye view](https://gitlab.ika.rwth-aachen.de/cam2bev/cam2bev-data/-/raw/master/2_F/examples/bev.png), [bird's eye view incl. occlusion](https://gitlab.ika.rwth-aachen.de/cam2bev/cam2bev-data/-/raw/master/2_F/examples/bev+occlusion.png), [homography view](https://gitlab.ika.rwth-aachen.de/cam2bev/cam2bev-data/-/raw/master/2_F/examples/homography.png) |","description_withheld":null,"homepage":"https://github.com/ika-rwth-aachen/Cam2BEV","introduced_date":"2020-05-08","introduced_date_note":null,"introduced_by":{"paper":"/paper/a-sim2real-deep-learning-approach-for-the","title":"A Sim2Real Deep Learning Approach for the Transformation of Images from Multiple Vehicle-Mounted Cameras to a Semantically Segmented Image in Bird's Eye View","first_author":"Lennart Reiher","url":null},"license":{"name":"Custom","url":"https://gitlab.ika.rwth-aachen.de/cam2bev/cam2bev-data/-/blob/master/LICENSE"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"Cross-View Image-to-Image Translation","url":"/task/cross-view-image-to-image-translation","datasets_with_task":"/datasets/task/cross-view-image-to-image-translation"}],"languages":[],"variants":["Cam2BEV"],"data_loaders":[{"repo":"https://github.com/ika-rwth-aachen/Cam2BEV","url":"https://github.com/ika-rwth-aachen/Cam2BEV","frameworks":["tf"]}],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/cross-view-image-to-image-translation-on-6","task":"Cross-View Image-to-Image Translation","dataset_variant":"Cam2BEV","rows":1,"metrics":["Mean IoU"],"first_row_in_archive_order":{"model":"uNetXST","paper":"/paper/a-sim2real-deep-learning-approach-for-the","metrics":{"Mean IoU":"71.92"},"code_links":[{"title":"ika-rwth-aachen/Cam2BEV","url":"https://github.com/ika-rwth-aachen/Cam2BEV"},{"title":"ika-rwth-aachen/etsi_its_messages","url":"https://github.com/ika-rwth-aachen/etsi_its_messages"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semantic-segmentation-on-cam2bev","task":"Semantic Segmentation","dataset_variant":"Cam2BEV","rows":1,"metrics":["Mean IoU"],"first_row_in_archive_order":{"model":"uNetXST","paper":"/paper/a-sim2real-deep-learning-approach-for-the","metrics":{"Mean IoU":"71.92"},"code_links":[{"title":"ika-rwth-aachen/Cam2BEV","url":"https://github.com/ika-rwth-aachen/Cam2BEV"},{"title":"ika-rwth-aachen/etsi_its_messages","url":"https://github.com/ika-rwth-aachen/etsi_its_messages"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/a-sim2real-deep-learning-approach-for-the","title":"A Sim2Real Deep Learning Approach for the Transformation of Images from Multiple Vehicle-Mounted Cameras to a Semantically Segmented Image in Bird's Eye View","date":"2020-05-08","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"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":1,"samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"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."}