{"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/bevstereo-enhancing-depth-estimation-in-multi","title":"BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereo","arxiv_id":"2209.10248","date":"2022-09-21","proceeding":null,"authors":["Yinhao Li","Han Bao","Zheng Ge","Jinrong Yang","Jianjian Sun","Zeming Li"],"abstract":"Bounded by the inherent ambiguity of depth perception, contemporary camera-based 3D object detection methods fall into the performance bottleneck. Intuitively, leveraging temporal multi-view stereo (MVS) technology is the natural knowledge for tackling this ambiguity. However, traditional attempts of MVS are flawed in two aspects when applying to 3D object detection scenes: 1) The affinity measurement among all views suffers expensive computation cost; 2) It is difficult to deal with outdoor scenarios where objects are often mobile. To this end, we introduce an effective temporal stereo method to dynamically select the scale of matching candidates, enable to significantly reduce computation overhead. Going one step further, we design an iterative algorithm to update more valuable candidates, making it adaptive to moving candidates. We instantiate our proposed method to multi-view 3D detector, namely BEVStereo. BEVStereo achieves the new state-of-the-art performance (i.e., 52.5% mAP and 61.0% NDS) on the camera-only track of nuScenes dataset. Meanwhile, extensive experiments reflect our method can deal with complex outdoor scenarios better than contemporary MVS approaches. Codes have been released at https://github.com/Megvii-BaseDetection/BEVStereo.","url_abs":"https://arxiv.org/abs/2209.10248v1","url_pdf":"https://arxiv.org/pdf/2209.10248v1.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":"bevstereo-enhancing-depth-estimation-in-multi","repo_url":"https://github.com/megvii-basedetection/bevstereo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"bevstereo-enhancing-depth-estimation-in-multi","repo_url":"https://github.com/ZRandomize/MatrixVT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"bevstereo-enhancing-depth-estimation-in-multi","repo_url":"https://github.com/megvii-basedetection/bevdepth","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"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":"BEVStereo","rank_in_archive_order":12,"of":19,"metrics":{"Future Frame":"false","NDS":"61.0"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2209.10248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.10248"}},"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/megvii-basedetection/bevstereo","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/megvii-basedetection/bevdepth","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ZRandomize/MatrixVT","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"samples":4,"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":0,"samples":[{"code_sha256_prefix":"75bd9e91eab5963b","entry":"bev_transform","repo":"ZRandomize/MatrixVT","repo_kind":"listed","path":"bevdepth/datasets/nusc_det_dataset.py","file_url":"https://github.com/ZRandomize/MatrixVT/blob/HEAD/bevdepth/datasets/nusc_det_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"75bd9e91eab5963b"}},{"code_sha256_prefix":"b0e6694828dcda80","entry":"generate_info","repo":"megvii-basedetection/bevstereo","repo_kind":"official","path":"scripts/gen_info.py","file_url":"https://github.com/megvii-basedetection/bevstereo/blob/HEAD/scripts/gen_info.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b0e6694828dcda80"}},{"code_sha256_prefix":"2dd096050170984b","entry":"get_rot","repo":"ZRandomize/MatrixVT","repo_kind":"listed","path":"bevdepth/datasets/nusc_det_dataset.py","file_url":"https://github.com/ZRandomize/MatrixVT/blob/HEAD/bevdepth/datasets/nusc_det_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2dd096050170984b"}},{"code_sha256_prefix":"42061d7d8a0c3f80","entry":"img_transform","repo":"ZRandomize/MatrixVT","repo_kind":"listed","path":"bevdepth/datasets/nusc_det_dataset.py","file_url":"https://github.com/ZRandomize/MatrixVT/blob/HEAD/bevdepth/datasets/nusc_det_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"42061d7d8a0c3f80"}},{"code_sha256_prefix":"bbbb5d6a28074b9d","entry":"is_parallel","repo":"ZRandomize/MatrixVT","repo_kind":"listed","path":"bevdepth/callbacks/ema.py","file_url":"https://github.com/ZRandomize/MatrixVT/blob/HEAD/bevdepth/callbacks/ema.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bbbb5d6a28074b9d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}