{"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/multi-view-3d-object-detection-network-for","title":"Multi-View 3D Object Detection Network for Autonomous Driving","arxiv_id":"1611.07759","date":"2016-11-23","proceeding":"CVPR 2017 7","authors":["Xiaozhi Chen","Huimin Ma","Ji Wan","Bo Li","Tian Xia"],"abstract":"This paper aims at high-accuracy 3D object detection in autonomous driving\nscenario. We propose Multi-View 3D networks (MV3D), a sensory-fusion framework\nthat takes both LIDAR point cloud and RGB images as input and predicts oriented\n3D bounding boxes. We encode the sparse 3D point cloud with a compact\nmulti-view representation. The network is composed of two subnetworks: one for\n3D object proposal generation and another for multi-view feature fusion. The\nproposal network generates 3D candidate boxes efficiently from the bird's eye\nview representation of 3D point cloud. We design a deep fusion scheme to\ncombine region-wise features from multiple views and enable interactions\nbetween intermediate layers of different paths. Experiments on the challenging\nKITTI benchmark show that our approach outperforms the state-of-the-art by\naround 25% and 30% AP on the tasks of 3D localization and 3D detection. In\naddition, for 2D detection, our approach obtains 10.3% higher AP than the\nstate-of-the-art on the hard data among the LIDAR-based methods.","url_abs":"http://arxiv.org/abs/1611.07759v3","url_pdf":"http://arxiv.org/pdf/1611.07759v3.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":"multi-view-3d-object-detection-network-for","repo_url":"https://github.com/aaronfriedman6/MV3D_VoxelNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"multi-view-3d-object-detection-network-for","repo_url":"https://github.com/bostondiditeam/MV3D","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"multi-view-3d-object-detection-network-for","repo_url":"https://github.com/shihaibi/MV3D","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-proposal-generation","task_name":"Object Proposal Generation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-object-detection-on-kitti-cars-easy-val","task":"3D Object Detection","dataset":"KITTI Cars Easy val","model":"MV3D","rank_in_archive_order":9,"of":11,"metrics":{"AP":"71.29"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-on-kitti-cars-easy-val","task":"3D Object Detection","dataset":"KITTI Cars Easy val","model":"MV3D (LiDAR)","rank_in_archive_order":10,"of":11,"metrics":{"AP":"71.19"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-on-kitti-cars-hard-val","task":"3D Object Detection","dataset":"KITTI Cars Hard val","model":"MV3D","rank_in_archive_order":9,"of":10,"metrics":{"AP":"56.56"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-on-kitti-cars-moderate-1","task":"3D Object Detection","dataset":"KITTI Cars Moderate val","model":"MV3D","rank_in_archive_order":10,"of":11,"metrics":{"AP":"62.68"},"uses_additional_data":false},{"leaderboard":"/sota/birds-eye-view-object-detection-on-kitti-cars-1","task":"Birds Eye View Object Detection","dataset":"KITTI Cars Easy val","model":"MV (BV+FV)","rank_in_archive_order":2,"of":2,"metrics":{"AP":"86.18"},"uses_additional_data":false},{"leaderboard":"/sota/birds-eye-view-object-detection-on-kitti-cars-3","task":"Birds Eye View Object Detection","dataset":"KITTI Cars Hard val","model":"MV (BV+FV)","rank_in_archive_order":2,"of":2,"metrics":{"AP":"76.33"},"uses_additional_data":false},{"leaderboard":"/sota/birds-eye-view-object-detection-on-kitti-cars-2","task":"Birds Eye View Object Detection","dataset":"KITTI Cars Moderate val","model":"MV (BV+FV)","rank_in_archive_order":3,"of":3,"metrics":{"AP":"77.32"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.07759","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.07759"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shihaibi/MV3D","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aaronfriedman6/MV3D_VoxelNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bostondiditeam/MV3D","reach":{"status":"ok"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":2,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"5ea1d7494b7eeb3a","entry":"draw_top_image","repo":"shihaibi/MV3D","repo_kind":"listed","path":"src/data.py","file_url":"https://github.com/shihaibi/MV3D/blob/HEAD/src/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5ea1d7494b7eeb3a"}},{"code_sha256_prefix":"fff650576097718b","entry":"obj_to_gt_boxes3d","repo":"shihaibi/MV3D","repo_kind":"listed","path":"src/data.py","file_url":"https://github.com/shihaibi/MV3D/blob/HEAD/src/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fff650576097718b"}},{"code_sha256_prefix":"4d58a266c48106eb","entry":"rgb_feature_net","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"4d58a266c48106eb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}