{"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/yolostereo3d-a-step-back-to-2d-for-efficient","title":"YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection","arxiv_id":"2103.09422","date":"2021-03-17","proceeding":null,"authors":["Yuxuan Liu","Lujia Wang","Ming Liu"],"abstract":"Object detection in 3D with stereo cameras is an important problem in computer vision, and is particularly crucial in low-cost autonomous mobile robots without LiDARs. Nowadays, most of the best-performing frameworks for stereo 3D object detection are based on dense depth reconstruction from disparity estimation, making them extremely computationally expensive. To enable real-world deployments of vision detection with binocular images, we take a step back to gain insights from 2D image-based detection frameworks and enhance them with stereo features. We incorporate knowledge and the inference structure from real-time one-stage 2D/3D object detector and introduce a light-weight stereo matching module. Our proposed framework, YOLOStereo3D, is trained on one single GPU and runs at more than ten fps. It demonstrates performance comparable to state-of-the-art stereo 3D detection frameworks without usage of LiDAR data. The code will be published in https://github.com/Owen-Liuyuxuan/visualDet3D.","url_abs":"https://arxiv.org/abs/2103.09422v1","url_pdf":"https://arxiv.org/pdf/2103.09422v1.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":"yolostereo3d-a-step-back-to-2d-for-efficient","repo_url":"https://github.com/Owen-Liuyuxuan/visualDet3D","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"yolostereo3d-a-step-back-to-2d-for-efficient","repo_url":"https://github.com/MindCode-4/code-5/tree/main/yolos","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"3d-object-detection-from-stereo-images","task_name":"3D Object Detection From Stereo Images"},{"task_slug":"disparity-estimation","task_name":"Disparity Estimation"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"stereo-matching-1","task_name":"Stereo Matching"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-object-detection-from-stereo-images-on-1","task":"3D Object Detection From Stereo Images","dataset":"KITTI Cars Moderate","model":"YoLoStereo3D","rank_in_archive_order":8,"of":12,"metrics":{"AP75":"41.25"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-from-stereo-images-on-2","task":"3D Object Detection From Stereo Images","dataset":"KITTI Pedestrians Moderate","model":"YoLoStereo3D","rank_in_archive_order":5,"of":6,"metrics":{"AP50":"19.75"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.09422","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}