{"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/ov-scan-semantically-consistent-alignment-for","title":"OV-SCAN: Semantically Consistent Alignment for Novel Object Discovery in Open-Vocabulary 3D Object Detection","arxiv_id":"2503.06435","date":"2025-03-09","proceeding":null,"authors":["Adrian Chow","Evelien Riddell","Yimu Wang","Sean Sedwards","Krzysztof Czarnecki"],"abstract":"Open-vocabulary 3D object detection for autonomous driving aims to detect novel objects beyond the predefined training label sets in point cloud scenes. Existing approaches achieve this by connecting traditional 3D object detectors with vision-language models (VLMs) to regress 3D bounding boxes for novel objects and perform open-vocabulary classification through cross-modal alignment between 3D and 2D features. However, achieving robust cross-modal alignment remains a challenge due to semantic inconsistencies when generating corresponding 3D and 2D feature pairs. To overcome this challenge, we present OV-SCAN, an Open-Vocabulary 3D framework that enforces Semantically Consistent Alignment for Novel object discovery. OV-SCAN employs two core strategies: discovering precise 3D annotations and filtering out low-quality or corrupted alignment pairs (arising from 3D annotation, occlusion-induced, or resolution-induced noise). Extensive experiments on the nuScenes dataset demonstrate that OV-SCAN achieves state-of-the-art performance.","url_abs":"https://arxiv.org/abs/2503.06435v1","url_pdf":"https://arxiv.org/pdf/2503.06435v1.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":[],"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-discovery","task_name":"Object Discovery"},{"task_slug":"cross-modal-alignment","task_name":"cross-modal alignment"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.06435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.06435"}},"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/ahtchow/OV-SCAN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":7},"by_repo_kind":{"found_in_text":{"samples":8,"ran":1,"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":"0d095007c24b14c0","entry":"post_act_block_dense","repo":"ahtchow/OV-SCAN","repo_kind":"found_in_text","path":"OV-SCAN/pcdet/models/backbones_3d/spconv_backbone_2d.py","file_url":"https://github.com/ahtchow/OV-SCAN/blob/HEAD/OV-SCAN/pcdet/models/backbones_3d/spconv_backbone_2d.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0d095007c24b14c0"}},{"code_sha256_prefix":"44db2351bcc0bffe","entry":"cfg_from_yaml_file","repo":"ahtchow/OV-SCAN","repo_kind":"found_in_text","path":"OV-SCAN/pcdet/config.py","file_url":"https://github.com/ahtchow/OV-SCAN/blob/HEAD/OV-SCAN/pcdet/config.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":"44db2351bcc0bffe"}},{"code_sha256_prefix":"65fe32ede00e7dcb","entry":"compute_fg_mask","repo":"ahtchow/OV-SCAN","repo_kind":"found_in_text","path":"OV-SCAN/pcdet/utils/loss_utils.py","file_url":"https://github.com/ahtchow/OV-SCAN/blob/HEAD/OV-SCAN/pcdet/utils/loss_utils.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":"65fe32ede00e7dcb"}},{"code_sha256_prefix":"1780d388cc532a6d","entry":"get_corner_loss_lidar","repo":"ahtchow/OV-SCAN","repo_kind":"found_in_text","path":"OV-SCAN/pcdet/utils/loss_utils.py","file_url":"https://github.com/ahtchow/OV-SCAN/blob/HEAD/OV-SCAN/pcdet/utils/loss_utils.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":"1780d388cc532a6d"}},{"code_sha256_prefix":"50e8e8cdfc5129f0","entry":"merge_new_config","repo":"ahtchow/OV-SCAN","repo_kind":"found_in_text","path":"OV-SCAN/pcdet/config.py","file_url":"https://github.com/ahtchow/OV-SCAN/blob/HEAD/OV-SCAN/pcdet/config.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":"50e8e8cdfc5129f0"}},{"code_sha256_prefix":"488b91d67a807558","entry":"neg_loss_cornernet","repo":"ahtchow/OV-SCAN","repo_kind":"found_in_text","path":"OV-SCAN/pcdet/utils/loss_utils.py","file_url":"https://github.com/ahtchow/OV-SCAN/blob/HEAD/OV-SCAN/pcdet/utils/loss_utils.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":"488b91d67a807558"}},{"code_sha256_prefix":"2b4e0558df870bf9","entry":"post_act_block","repo":"ahtchow/OV-SCAN","repo_kind":"found_in_text","path":"OV-SCAN/pcdet/models/backbones_3d/spconv_backbone.py","file_url":"https://github.com/ahtchow/OV-SCAN/blob/HEAD/OV-SCAN/pcdet/models/backbones_3d/spconv_backbone.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":"2b4e0558df870bf9"}},{"code_sha256_prefix":"016a882194742fe9","entry":"post_act_block","repo":"ahtchow/OV-SCAN","repo_kind":"found_in_text","path":"OV-SCAN/pcdet/models/backbones_3d/spconv_backbone_2d.py","file_url":"https://github.com/ahtchow/OV-SCAN/blob/HEAD/OV-SCAN/pcdet/models/backbones_3d/spconv_backbone_2d.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":"016a882194742fe9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}