{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/simbev-a-synthetic-multi-task-multi-sensor","title":"SimBEV: A Synthetic Multi-Task Multi-Sensor Driving Data Generation Tool and Dataset","arxiv_id":"2502.01894","date":"2025-02-04","proceeding":null,"authors":["Goodarz Mehr","Azim Eskandarian"],"abstract":"Bird's-eye view (BEV) perception has garnered significant attention in autonomous driving in recent years, in part because BEV representation facilitates multi-modal sensor fusion. BEV representation enables a variety of perception tasks including BEV segmentation, a concise view of the environment useful for planning a vehicle's trajectory. However, this representation is not fully supported by existing datasets, and creation of new datasets for this purpose can be a time-consuming endeavor. To address this challenge, we introduce SimBEV. SimBEV is a randomized synthetic data generation tool that is extensively configurable and scalable, supports a wide array of sensors, incorporates information from multiple sources to capture accurate BEV ground truth, and enables a variety of perception tasks including BEV segmentation and 3D object detection. SimBEV is used to create the SimBEV dataset, a large collection of annotated perception data from diverse driving scenarios. SimBEV and the SimBEV dataset are open and available to the public.","url_abs":"https://arxiv.org/abs/2502.01894v2","url_pdf":"https://arxiv.org/pdf/2502.01894v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"simbev-a-synthetic-multi-task-multi-sensor","repo_url":"https://github.com/goodarzmehr/simbev","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"bev-segmentation","task_name":"BEV Segmentation"},{"task_slug":"bird-s-eye-view-semantic-segmentation","task_name":"Bird's-Eye View Semantic Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"sensor-fusion","task_name":"Sensor Fusion"},{"task_slug":"synthetic-data-generation","task_name":"Synthetic Data Generation"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[{"slug":"simbev","name":"SimBEV","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-object-detection-on-simbev","task":"3D Object Detection","dataset":"SimBEV","model":"UniTR+LSS","rank_in_archive_order":1,"of":5,"metrics":{"SDS":"0.622","mAOE":"0.207","mAP":"0.478","mASE":"0.085","mATE":"0.113","mAVE":"0.53"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-on-simbev","task":"3D Object Detection","dataset":"SimBEV","model":"UniTR","rank_in_archive_order":2,"of":5,"metrics":{"SDS":"0.617","mAOE":"0.224","mAP":"0.477","mASE":"0.09","mATE":"0.113","mAVE":"0.55"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-on-simbev","task":"3D Object Detection","dataset":"SimBEV","model":"BEVFusion","rank_in_archive_order":3,"of":5,"metrics":{"SDS":"0.566","mAOE":"0.122","mAP":"0.481","mASE":"0.127","mATE":"0.146","mAVE":"1.54"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-on-simbev","task":"3D Object Detection","dataset":"SimBEV","model":"BEVFusion-L","rank_in_archive_order":4,"of":5,"metrics":{"SDS":"0.564","mAOE":"0.133","mAP":"0.481","mASE":"0.134","mATE":"0.144","mAVE":"1.56"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-on-simbev","task":"3D Object Detection","dataset":"SimBEV","model":"BEVFusion-C","rank_in_archive_order":5,"of":5,"metrics":{"SDS":"0.251","mAOE":"1.044","mAP":"0.221","mASE":"0.137","mATE":"0.744","mAVE":"4.65"},"uses_additional_data":false},{"leaderboard":"/sota/bev-segmentation-on-simbev","task":"BEV Segmentation","dataset":"SimBEV","model":"BEVFusion","rank_in_archive_order":1,"of":5,"metrics":{"bicycle":"0.036","bus":"0.8","car":"0.727","mIoU":"0.5","motorcycle":"0.363","pedestrian":"0.2","rider":"0.233","road":"0.884","truck":"0.745"},"uses_additional_data":false},{"leaderboard":"/sota/bev-segmentation-on-simbev","task":"BEV Segmentation","dataset":"SimBEV","model":"UniTR","rank_in_archive_order":2,"of":5,"metrics":{"bicycle":"0.114","bus":"0.517","car":"0.738","mIoU":"0.497","motorcycle":"0.365","pedestrian":"0.275","rider":"0.362","road":"0.928","truck":"0.677"},"uses_additional_data":false},{"leaderboard":"/sota/bev-segmentation-on-simbev","task":"BEV Segmentation","dataset":"SimBEV","model":"BEVFusion-L","rank_in_archive_order":3,"of":5,"metrics":{"bicycle":"0.036","bus":"0.815","car":"0.706","mIoU":"0.483","motorcycle":"0.325","pedestrian":"0.189","rider":"0.184","road":"0.877","truck":"0.735"},"uses_additional_data":false},{"leaderboard":"/sota/bev-segmentation-on-simbev","task":"BEV Segmentation","dataset":"SimBEV","model":"UniTR+LSS","rank_in_archive_order":4,"of":5,"metrics":{"bicycle":"0.063","bus":"0.585","car":"0.728","mIoU":"0.476","motorcycle":"0.359","pedestrian":"0.129","rider":"0.316","road":"0.933","truck":"0.694"},"uses_additional_data":false},{"leaderboard":"/sota/bev-segmentation-on-simbev","task":"BEV Segmentation","dataset":"SimBEV","model":"BEVFusion-C","rank_in_archive_order":5,"of":5,"metrics":{"bicycle":"0","bus":"0.229","car":"0.172","mIoU":"0.152","motorcycle":"0","pedestrian":"0","rider":"0","road":"0.76","truck":"0.051"},"uses_additional_data":false},{"leaderboard":"/sota/bird-s-eye-view-semantic-segmentation-on-1","task":"Bird's-Eye View Semantic Segmentation","dataset":"SimBEV","model":"BEVFusion","rank_in_archive_order":1,"of":5,"metrics":{"bicycle":"0.036","bus":"0.808","car":"0.727","mIoU":"0.5","motorcycle":"0.363","pedestrian":"0.202","rider":"0.233","road":"0.884","truck":"0.745"},"uses_additional_data":false},{"leaderboard":"/sota/bird-s-eye-view-semantic-segmentation-on-1","task":"Bird's-Eye View Semantic Segmentation","dataset":"SimBEV","model":"UniTR","rank_in_archive_order":2,"of":5,"metrics":{"bicycle":"0.114","bus":"0.517","car":"0.738","mIoU":"0.497","motorcycle":"0.365","pedestrian":"0.275","rider":"0.362","road":"0.928","truck":"0.677"},"uses_additional_data":false},{"leaderboard":"/sota/bird-s-eye-view-semantic-segmentation-on-1","task":"Bird's-Eye View Semantic Segmentation","dataset":"SimBEV","model":"BEVFusion-L","rank_in_archive_order":3,"of":5,"metrics":{"bicycle":"0.036","bus":"0.815","car":"0.706","mIoU":"0.483","motorcycle":"0.325","pedestrian":"0.189","rider":"0.184","road":"0.877","truck":"0.735"},"uses_additional_data":false},{"leaderboard":"/sota/bird-s-eye-view-semantic-segmentation-on-1","task":"Bird's-Eye View Semantic Segmentation","dataset":"SimBEV","model":"UniTR+LSS","rank_in_archive_order":4,"of":5,"metrics":{"bicycle":"0.063","bus":"0.585","car":"0.728","mIoU":"0.476","motorcycle":"0.359","pedestrian":"0.129","rider":"0.316","road":"0.933","truck":"0.694"},"uses_additional_data":false},{"leaderboard":"/sota/bird-s-eye-view-semantic-segmentation-on-1","task":"Bird's-Eye View Semantic Segmentation","dataset":"SimBEV","model":"BEVFusion-C","rank_in_archive_order":5,"of":5,"metrics":{"bicycle":"0","bus":"0.229","car":"0.172","mIoU":"0.152","motorcycle":"0","pedestrian":"0","rider":"0","road":"0.76","truck":"0.051"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}