{"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/leveraging-vision-centric-multi-modal-1","title":"Leveraging Vision-Centric Multi-Modal Expertise for 3D Object Detection","arxiv_id":"2310.15670","date":"2023-10-24","proceeding":"NeurIPS 2023 11","authors":["Linyan Huang","Zhiqi Li","Chonghao Sima","Wenhai Wang","Jingdong Wang","Yu Qiao","Hongyang Li"],"abstract":"Current research is primarily dedicated to advancing the accuracy of camera-only 3D object detectors (apprentice) through the knowledge transferred from LiDAR- or multi-modal-based counterparts (expert). However, the presence of the domain gap between LiDAR and camera features, coupled with the inherent incompatibility in temporal fusion, significantly hinders the effectiveness of distillation-based enhancements for apprentices. Motivated by the success of uni-modal distillation, an apprentice-friendly expert model would predominantly rely on camera features, while still achieving comparable performance to multi-modal models. To this end, we introduce VCD, a framework to improve the camera-only apprentice model, including an apprentice-friendly multi-modal expert and temporal-fusion-friendly distillation supervision. The multi-modal expert VCD-E adopts an identical structure as that of the camera-only apprentice in order to alleviate the feature disparity, and leverages LiDAR input as a depth prior to reconstruct the 3D scene, achieving the performance on par with other heterogeneous multi-modal experts. Additionally, a fine-grained trajectory-based distillation module is introduced with the purpose of individually rectifying the motion misalignment for each object in the scene. With those improvements, our camera-only apprentice VCD-A sets new state-of-the-art on nuScenes with a score of 63.1% NDS.","url_abs":"https://arxiv.org/abs/2310.15670v1","url_pdf":"https://arxiv.org/pdf/2310.15670v1.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":"leveraging-vision-centric-multi-modal-1","repo_url":"https://github.com/opendrivelab/birds-eye-view-perception","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-object-detection-on-nuscenes-camera-only","task":"3D Object Detection","dataset":"nuScenes Camera Only","model":"VCD-A","rank_in_archive_order":6,"of":19,"metrics":{"Future Frame":"false","NDS":"67.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.15670","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.15670"}},"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":"deterministic:regex_extraction","url":"https://github.com/OpenDriveLab/Birds-eye-view-Perception","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/opendrivelab/birds-eye-view-perception","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":0,"samples":[{"code_sha256_prefix":"d6f1a151dcb09c1f","entry":"horizontal_flip_image_multiview","repo":"OpenDriveLab/Birds-eye-view-Perception","repo_kind":"official","path":"bev_toolbox/data_aug/functional.py","file_url":"https://github.com/OpenDriveLab/Birds-eye-view-Perception/blob/HEAD/bev_toolbox/data_aug/functional.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d6f1a151dcb09c1f"}},{"code_sha256_prefix":"6b894132bebbea7e","entry":"scale_image_multiple_view","repo":"OpenDriveLab/Birds-eye-view-Perception","repo_kind":"official","path":"bev_toolbox/data_aug/functional.py","file_url":"https://github.com/OpenDriveLab/Birds-eye-view-Perception/blob/HEAD/bev_toolbox/data_aug/functional.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6b894132bebbea7e"}},{"code_sha256_prefix":"2bbcfd0ababb1e92","entry":"vertical_flip_image_multiview","repo":"OpenDriveLab/Birds-eye-view-Perception","repo_kind":"official","path":"bev_toolbox/data_aug/functional.py","file_url":"https://github.com/OpenDriveLab/Birds-eye-view-Perception/blob/HEAD/bev_toolbox/data_aug/functional.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2bbcfd0ababb1e92"}},{"code_sha256_prefix":"f6a173f4830f978c","entry":"gen_dx_bx","repo":"OpenDriveLab/Birds-eye-view-Perception","repo_kind":"official","path":"nuScenes_playground/VCD/mmdet3d/models/necks/view_transformer.py","file_url":"https://github.com/OpenDriveLab/Birds-eye-view-Perception/blob/HEAD/nuScenes_playground/VCD/mmdet3d/models/necks/view_transformer.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f6a173f4830f978c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}