{"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/joint-3d-proposal-generation-and-object","title":"Joint 3D Proposal Generation and Object Detection from View Aggregation","arxiv_id":"1712.02294","date":"2017-12-06","proceeding":null,"authors":["Jason Ku","Melissa Mozifian","Jungwook Lee","Ali Harakeh","Steven Waslander"],"abstract":"We present AVOD, an Aggregate View Object Detection network for autonomous\ndriving scenarios. The proposed neural network architecture uses LIDAR point\nclouds and RGB images to generate features that are shared by two subnetworks:\na region proposal network (RPN) and a second stage detector network. The\nproposed RPN uses a novel architecture capable of performing multimodal feature\nfusion on high resolution feature maps to generate reliable 3D object proposals\nfor multiple object classes in road scenes. Using these proposals, the second\nstage detection network performs accurate oriented 3D bounding box regression\nand category classification to predict the extents, orientation, and\nclassification of objects in 3D space. Our proposed architecture is shown to\nproduce state of the art results on the KITTI 3D object detection benchmark\nwhile running in real time with a low memory footprint, making it a suitable\ncandidate for deployment on autonomous vehicles. Code is at:\nhttps://github.com/kujason/avod","url_abs":"http://arxiv.org/abs/1712.02294v4","url_pdf":"http://arxiv.org/pdf/1712.02294v4.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":"joint-3d-proposal-generation-and-object","repo_url":"https://github.com/kujason/avod","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"joint-3d-proposal-generation-and-object","repo_url":"https://github.com/Fredrik00/avod","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"joint-3d-proposal-generation-and-object","repo_url":"https://github.com/asharakeh/kitti_native_evaluation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"joint-3d-proposal-generation-and-object","repo_url":"https://github.com/kujason/ip_basic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"autonomous-vehicles","task_name":"Autonomous Vehicles"},{"task_slug":"classification","task_name":"General Classification"},{"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"}],"methods":[{"method_slug":"rpn","method_name":"RPN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-object-detection-on-kitti-cars-easy","task":"3D Object Detection","dataset":"KITTI Cars Easy","model":"AVOD + Feature Pyramid","rank_in_archive_order":21,"of":26,"metrics":{"AP":"81.94%"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-on-kitti-cars-hard","task":"3D Object Detection","dataset":"KITTI Cars Hard","model":"AVOD + Feature Pyramid","rank_in_archive_order":19,"of":25,"metrics":{"AP":"66.38%"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-on-kitti-cyclists-easy","task":"3D Object Detection","dataset":"KITTI Cyclists Easy","model":"AVOD + Feature Pyramid","rank_in_archive_order":11,"of":12,"metrics":{"AP":"64.0%"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-on-kitti-cyclists-hard","task":"3D Object Detection","dataset":"KITTI Cyclists Hard","model":"AVOD + Feature Pyramid","rank_in_archive_order":11,"of":12,"metrics":{"AP":"46.61%"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-on-kitti-cyclists","task":"3D Object Detection","dataset":"KITTI Cyclists Moderate","model":"AVOD + Feature Pyramid","rank_in_archive_order":12,"of":13,"metrics":{"AP":"52.18%"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-on-kitti-pedestrians-easy","task":"3D Object Detection","dataset":"KITTI Pedestrians Easy","model":"AVOD + Feature Pyramid","rank_in_archive_order":7,"of":9,"metrics":{"AP":"50.8%"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-on-kitti-pedestrians-hard","task":"3D Object Detection","dataset":"KITTI Pedestrians Hard","model":"AVOD + Feature Pyramid","rank_in_archive_order":5,"of":9,"metrics":{"AP":"40.88%"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-on-kitti-pedestrians","task":"3D Object Detection","dataset":"KITTI Pedestrians Moderate","model":"AVOD + Feature Pyramid","rank_in_archive_order":8,"of":12,"metrics":{"AP":"42.81%"},"uses_additional_data":false},{"leaderboard":"/sota/birds-eye-view-object-detection-on-kitti-cars-4","task":"Birds Eye View Object Detection","dataset":"KITTI Cars Easy","model":"AVOD-FPN","rank_in_archive_order":7,"of":9,"metrics":{"AP":"88.53"},"uses_additional_data":false},{"leaderboard":"/sota/birds-eye-view-object-detection-on-kitti-cars","task":"Birds Eye View Object Detection","dataset":"KITTI Cars Moderate","model":"AVOD-FPN","rank_in_archive_order":7,"of":9,"metrics":{"AP":"83.79%"},"uses_additional_data":false},{"leaderboard":"/sota/birds-eye-view-object-detection-on-kitti","task":"Birds Eye View Object Detection","dataset":"KITTI Cyclists Moderate","model":"AVOD-FPN","rank_in_archive_order":5,"of":6,"metrics":{"AP":"57.48%"},"uses_additional_data":false},{"leaderboard":"/sota/birds-eye-view-object-detection-on-kitti-1","task":"Birds Eye View Object Detection","dataset":"KITTI Pedestrians Moderate","model":"AVOD-FPN","rank_in_archive_order":3,"of":6,"metrics":{"AP":"51.05%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1712.02294","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}