{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7LQSB7VWCUOU35QED4YSGETZZD","short_pith_number":"pith:7LQSB7VW","schema_version":"1.0","canonical_sha256":"fae120feb6151d4df6041f31231279c8c7019823c9e3f784ed9c78439f52ce82","source":{"kind":"arxiv","id":"1912.13192","version":2},"attestation_state":"computed","paper":{"title":"PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Chaoxu Guo, Hongsheng Li, Jianping Shi, Li Jiang, Shaoshuai Shi, Xiaogang Wang, Zhe Wang","submitted_at":"2019-12-31T06:34:10Z","abstract_excerpt":"We present a novel and high-performance 3D object detection framework, named PointVoxel-RCNN (PV-RCNN), for accurate 3D object detection from point clouds. Our proposed method deeply integrates both 3D voxel Convolutional Neural Network (CNN) and PointNet-based set abstraction to learn more discriminative point cloud features. It takes advantages of efficient learning and high-quality proposals of the 3D voxel CNN and the flexible receptive fields of the PointNet-based networks. Specifically, the proposed framework summarizes the 3D scene with a 3D voxel CNN into a small set of keypoints via a"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1912.13192","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-12-31T06:34:10Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"179b47c58dc0a460514b49ff134c36753703b0f319a538bfd1790dd77e527766","abstract_canon_sha256":"59be019ecf8d2606e3ff44c615ff7aa70563849611546ecf65c26bbfa79b6b93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:27.485972Z","signature_b64":"FQ81NK5FQfwr4GuAQycFiiT4yDDKI8swnC1HtCkXYxxTSgxsDlyriNjytqfGFuoYR8OpQLA3pc0HcOBw8RGmDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fae120feb6151d4df6041f31231279c8c7019823c9e3f784ed9c78439f52ce82","last_reissued_at":"2026-07-05T02:30:27.485445Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:27.485445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Chaoxu Guo, Hongsheng Li, Jianping Shi, Li Jiang, Shaoshuai Shi, Xiaogang Wang, Zhe Wang","submitted_at":"2019-12-31T06:34:10Z","abstract_excerpt":"We present a novel and high-performance 3D object detection framework, named PointVoxel-RCNN (PV-RCNN), for accurate 3D object detection from point clouds. Our proposed method deeply integrates both 3D voxel Convolutional Neural Network (CNN) and PointNet-based set abstraction to learn more discriminative point cloud features. It takes advantages of efficient learning and high-quality proposals of the 3D voxel CNN and the flexible receptive fields of the PointNet-based networks. Specifically, the proposed framework summarizes the 3D scene with a 3D voxel CNN into a small set of keypoints via a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.13192","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.13192/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1912.13192","created_at":"2026-07-05T02:30:27.485507+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.13192v2","created_at":"2026-07-05T02:30:27.485507+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.13192","created_at":"2026-07-05T02:30:27.485507+00:00"},{"alias_kind":"pith_short_12","alias_value":"7LQSB7VWCUOU","created_at":"2026-07-05T02:30:27.485507+00:00"},{"alias_kind":"pith_short_16","alias_value":"7LQSB7VWCUOU35QE","created_at":"2026-07-05T02:30:27.485507+00:00"},{"alias_kind":"pith_short_8","alias_value":"7LQSB7VW","created_at":"2026-07-05T02:30:27.485507+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02370","citing_title":"A Simulation Platform for Flapping-Wing Vehicles","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7LQSB7VWCUOU35QED4YSGETZZD","json":"https://pith.science/pith/7LQSB7VWCUOU35QED4YSGETZZD.json","graph_json":"https://pith.science/api/pith-number/7LQSB7VWCUOU35QED4YSGETZZD/graph.json","events_json":"https://pith.science/api/pith-number/7LQSB7VWCUOU35QED4YSGETZZD/events.json","paper":"https://pith.science/paper/7LQSB7VW"},"agent_actions":{"view_html":"https://pith.science/pith/7LQSB7VWCUOU35QED4YSGETZZD","download_json":"https://pith.science/pith/7LQSB7VWCUOU35QED4YSGETZZD.json","view_paper":"https://pith.science/paper/7LQSB7VW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.13192&json=true","fetch_graph":"https://pith.science/api/pith-number/7LQSB7VWCUOU35QED4YSGETZZD/graph.json","fetch_events":"https://pith.science/api/pith-number/7LQSB7VWCUOU35QED4YSGETZZD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7LQSB7VWCUOU35QED4YSGETZZD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7LQSB7VWCUOU35QED4YSGETZZD/action/storage_attestation","attest_author":"https://pith.science/pith/7LQSB7VWCUOU35QED4YSGETZZD/action/author_attestation","sign_citation":"https://pith.science/pith/7LQSB7VWCUOU35QED4YSGETZZD/action/citation_signature","submit_replication":"https://pith.science/pith/7LQSB7VWCUOU35QED4YSGETZZD/action/replication_record"}},"created_at":"2026-07-05T02:30:27.485507+00:00","updated_at":"2026-07-05T02:30:27.485507+00:00"}