{"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/complex-yolo-real-time-3d-object-detection-on","title":"Complex-YOLO: Real-time 3D Object Detection on Point Clouds","arxiv_id":"1803.06199","date":"2018-03-16","proceeding":null,"authors":["Martin Simon","Stefan Milz","Karl Amende","Horst-Michael Gross"],"abstract":"Lidar based 3D object detection is inevitable for autonomous driving, because\nit directly links to environmental understanding and therefore builds the base\nfor prediction and motion planning. The capacity of inferencing highly sparse\n3D data in real-time is an ill-posed problem for lots of other application\nareas besides automated vehicles, e.g. augmented reality, personal robotics or\nindustrial automation. We introduce Complex-YOLO, a state of the art real-time\n3D object detection network on point clouds only. In this work, we describe a\nnetwork that expands YOLOv2, a fast 2D standard object detector for RGB images,\nby a specific complex regression strategy to estimate multi-class 3D boxes in\nCartesian space. Thus, we propose a specific Euler-Region-Proposal Network\n(E-RPN) to estimate the pose of the object by adding an imaginary and a real\nfraction to the regression network. This ends up in a closed complex space and\navoids singularities, which occur by single angle estimations. The E-RPN\nsupports to generalize well during training. Our experiments on the KITTI\nbenchmark suite show that we outperform current leading methods for 3D object\ndetection specifically in terms of efficiency. We achieve state of the art\nresults for cars, pedestrians and cyclists by being more than five times faster\nthan the fastest competitor. Further, our model is capable of estimating all\neight KITTI-classes, including Vans, Trucks or sitting pedestrians\nsimultaneously with high accuracy.","url_abs":"http://arxiv.org/abs/1803.06199v2","url_pdf":"http://arxiv.org/pdf/1803.06199v2.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":"complex-yolo-real-time-3d-object-detection-on","repo_url":"https://github.com/RichardMinsooGo-ML/Pytorch-Complex-Yolo-Yolov3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"complex-yolo-real-time-3d-object-detection-on","repo_url":"https://github.com/RichardMinsooGo-ML/Pytorch-Complex-Yolo-Yolov4","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"complex-yolo-real-time-3d-object-detection-on","repo_url":"https://github.com/RichardMinsooGo-ML/Pytorch-Yolo-3d-Yolov3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"complex-yolo-real-time-3d-object-detection-on","repo_url":"https://github.com/RichardMinsooGo-ML/Pytorch-Yolo-3d-Yolov4","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"complex-yolo-real-time-3d-object-detection-on","repo_url":"https://github.com/dC4rlos/TFM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"complex-yolo-real-time-3d-object-detection-on","repo_url":"https://github.com/ghimiredhikura/Complex-YOLO-V3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"complex-yolo-real-time-3d-object-detection-on","repo_url":"https://github.com/ghimiredhikura/Complex-YOLOv3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"complex-yolo-real-time-3d-object-detection-on","repo_url":"https://github.com/maudzung/Complex-YOLOv4-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"complex-yolo-real-time-3d-object-detection-on","repo_url":"https://github.com/wwooo/tensorflow_complex_yolo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}},{"paper_slug":"complex-yolo-real-time-3d-object-detection-on","repo_url":"https://github.com/AI-liu/Complex-YOLO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"motion-planning","task_name":"Motion Planning"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"region-proposal","task_name":"Region Proposal"},{"task_slug":"object-detection-1","task_name":"object-detection"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"darknet-19","method_name":"Darknet-19"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"yolov2","method_name":"YOLOv2"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1803.06199","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}