{"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/3d-dual-fusion-dual-domain-dual-query-camera-1","title":"3D Dual-Fusion: Dual-Domain Dual-Query Camera-LiDAR Fusion for 3D Object Detection","arxiv_id":"2211.13529","date":"2022-11-24","proceeding":null,"authors":["Yecheol Kim","Konyul Park","Minwook Kim","Dongsuk Kum","Jun Won Choi"],"abstract":"Fusing data from cameras and LiDAR sensors is an essential technique to achieve robust 3D object detection. One key challenge in camera-LiDAR fusion involves mitigating the large domain gap between the two sensors in terms of coordinates and data distribution when fusing their features. In this paper, we propose a novel camera-LiDAR fusion architecture called, 3D Dual-Fusion, which is designed to mitigate the gap between the feature representations of camera and LiDAR data. The proposed method fuses the features of the camera-view and 3D voxel-view domain and models their interactions through deformable attention. We redesign the transformer fusion encoder to aggregate the information from the two domains. Two major changes include 1) dual query-based deformable attention to fuse the dual-domain features interactively and 2) 3D local self-attention to encode the voxel-domain queries prior to dual-query decoding. The results of an experimental evaluation show that the proposed camera-LiDAR fusion architecture achieved competitive performance on the KITTI and nuScenes datasets, with state-of-the-art performances in some 3D object detection benchmarks categories.","url_abs":"https://arxiv.org/abs/2211.13529v2","url_pdf":"https://arxiv.org/pdf/2211.13529v2.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":"3d-dual-fusion-dual-domain-dual-query-camera-1","repo_url":"https://github.com/rasd3/3D-Dual-Fusion","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"robust-3d-object-detection","task_name":"Robust 3D Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-object-detection-on-kitti-cars-easy","task":"3D Object Detection","dataset":"KITTI Cars Easy","model":"3D Dual-Fusion","rank_in_archive_order":5,"of":26,"metrics":{"AP":"91.01%"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-on-kitti-cars-hard","task":"3D Object Detection","dataset":"KITTI Cars Hard","model":"3D Dual-Fusion","rank_in_archive_order":2,"of":25,"metrics":{"AP":"79.39%"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-on-nuscenes","task":"3D Object Detection","dataset":"nuScenes","model":"3D Dual-Fusion_T","rank_in_archive_order":29,"of":372,"metrics":{"NDS":"0.73","mAAE":"0.13","mAOE":"0.33","mAP":"0.71","mASE":"0.24","mATE":"0.26","mAVE":"0.27"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2211.13529","atlas_url":"https://app.syntology.ai/?focus=2211.13529","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}