{"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/dvpe-divided-view-position-embedding-for","title":"DVPE: Divided View Position Embedding for Multi-View 3D Object Detection","arxiv_id":"2407.16955","date":"2024-07-24","proceeding":null,"authors":["Jiasen Wang","Zhenglin Li","Ke Sun","Xianyuan Liu","Yang Zhou"],"abstract":"Sparse query-based paradigms have achieved significant success in multi-view 3D detection for autonomous vehicles. Current research faces challenges in balancing between enlarging receptive fields and reducing interference when aggregating multi-view features. Moreover, different poses of cameras present challenges in training global attention models. To address these problems, this paper proposes a divided view method, in which features are modeled globally via the visibility crossattention mechanism, but interact only with partial features in a divided local virtual space. This effectively reduces interference from other irrelevant features and alleviates the training difficulties of the transformer by decoupling the position embedding from camera poses. Additionally, 2D historical RoI features are incorporated into the object-centric temporal modeling to utilize highlevel visual semantic information. The model is trained using a one-to-many assignment strategy to facilitate stability. Our framework, named DVPE, achieves state-of-the-art performance (57.2% mAP and 64.5% NDS) on the nuScenes test set. Codes will be available at https://github.com/dop0/DVPE.","url_abs":"https://arxiv.org/abs/2407.16955v1","url_pdf":"https://arxiv.org/pdf/2407.16955v1.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":"dvpe-divided-view-position-embedding-for","repo_url":"https://github.com/dop0/dvpe","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":"autonomous-vehicles","task_name":"Autonomous Vehicles"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":null,"task_name":"Position"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.16955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.16955"}},"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/dop0/DVPE","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":6,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"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":"c637c42a302bb63c","entry":"conv1x1","repo":"dop0/DVPE","repo_kind":"official","path":"projects/mmdet3d_plugin/models/backbones/vovnet.py","file_url":"https://github.com/dop0/DVPE/blob/HEAD/projects/mmdet3d_plugin/models/backbones/vovnet.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":"c637c42a302bb63c"}},{"code_sha256_prefix":"303f4d3695ad18f1","entry":"conv3x3","repo":"dop0/DVPE","repo_kind":"official","path":"projects/mmdet3d_plugin/models/backbones/vovnet.py","file_url":"https://github.com/dop0/DVPE/blob/HEAD/projects/mmdet3d_plugin/models/backbones/vovnet.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":"303f4d3695ad18f1"}},{"code_sha256_prefix":"8f56a924d9b7a236","entry":"convert_egopose_to_matrix_numpy","repo":"dop0/DVPE","repo_kind":"official","path":"projects/mmdet3d_plugin/datasets/nuscenes_dataset.py","file_url":"https://github.com/dop0/DVPE/blob/HEAD/projects/mmdet3d_plugin/datasets/nuscenes_dataset.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":"8f56a924d9b7a236"}},{"code_sha256_prefix":"4a1654634c1825a8","entry":"denormalize_bbox","repo":"dop0/DVPE","repo_kind":"official","path":"projects/mmdet3d_plugin/core/bbox/util.py","file_url":"https://github.com/dop0/DVPE/blob/HEAD/projects/mmdet3d_plugin/core/bbox/util.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":"4a1654634c1825a8"}},{"code_sha256_prefix":"35ab6b84b360dfb4","entry":"invert_matrix_egopose_numpy","repo":"dop0/DVPE","repo_kind":"official","path":"projects/mmdet3d_plugin/datasets/nuscenes_dataset.py","file_url":"https://github.com/dop0/DVPE/blob/HEAD/projects/mmdet3d_plugin/datasets/nuscenes_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"35ab6b84b360dfb4"}},{"code_sha256_prefix":"a18ca9ff1a1b82c8","entry":"normalize_bbox","repo":"dop0/DVPE","repo_kind":"official","path":"projects/mmdet3d_plugin/core/bbox/util.py","file_url":"https://github.com/dop0/DVPE/blob/HEAD/projects/mmdet3d_plugin/core/bbox/util.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":"a18ca9ff1a1b82c8"}},{"code_sha256_prefix":"5ebf15e6940f6710","entry":"dw_conv3x3","repo":"dop0/DVPE","repo_kind":"official","path":"projects/mmdet3d_plugin/models/backbones/vovnet.py","file_url":"https://github.com/dop0/DVPE/blob/HEAD/projects/mmdet3d_plugin/models/backbones/vovnet.py","link_basis":"first_harvest_node","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":"5ebf15e6940f6710"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}