{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:I3KEP3XELKBEWAPKZTJSL2HHVF","short_pith_number":"pith:I3KEP3XE","schema_version":"1.0","canonical_sha256":"46d447eee45a824b01eaccd325e8e7a96edcf700cee139161ac73932479735f0","source":{"kind":"arxiv","id":"1907.06038","version":2},"attestation_state":"computed","paper":{"title":"M3D-RPN: Monocular 3D Region Proposal Network for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Garrick Brazil, Xiaoming Liu","submitted_at":"2019-07-13T09:40:22Z","abstract_excerpt":"Understanding the world in 3D is a critical component of urban autonomous driving. Generally, the combination of expensive LiDAR sensors and stereo RGB imaging has been paramount for successful 3D object detection algorithms, whereas monocular image-only methods experience drastically reduced performance. We propose to reduce the gap by reformulating the monocular 3D detection problem as a standalone 3D region proposal network. We leverage the geometric relationship of 2D and 3D perspectives, allowing 3D boxes to utilize well-known and powerful convolutional features generated in the image-spa"},"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":"1907.06038","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-13T09:40:22Z","cross_cats_sorted":[],"title_canon_sha256":"23e14b42c0c4dcb08efe3aba19886f3bb06b765a3c24aecd70033875b7df57be","abstract_canon_sha256":"b0e1048300958115ef8cf628ddeaf513b78eec37c08a60163170e4e223685caa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:53:15.104545Z","signature_b64":"TrsG+i8PLWercvbuL6w2woBb6m5LT1DZ9XMpPEPJpiqn/qjJdbzNrl8Uk6Cf2I7vdlIl2Xd7BMXwlZ7yz3hTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46d447eee45a824b01eaccd325e8e7a96edcf700cee139161ac73932479735f0","last_reissued_at":"2026-07-04T23:53:15.104079Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:53:15.104079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M3D-RPN: Monocular 3D Region Proposal Network for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Garrick Brazil, Xiaoming Liu","submitted_at":"2019-07-13T09:40:22Z","abstract_excerpt":"Understanding the world in 3D is a critical component of urban autonomous driving. Generally, the combination of expensive LiDAR sensors and stereo RGB imaging has been paramount for successful 3D object detection algorithms, whereas monocular image-only methods experience drastically reduced performance. We propose to reduce the gap by reformulating the monocular 3D detection problem as a standalone 3D region proposal network. We leverage the geometric relationship of 2D and 3D perspectives, allowing 3D boxes to utilize well-known and powerful convolutional features generated in the image-spa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.06038","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/1907.06038/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":"1907.06038","created_at":"2026-07-04T23:53:15.104141+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.06038v2","created_at":"2026-07-04T23:53:15.104141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.06038","created_at":"2026-07-04T23:53:15.104141+00:00"},{"alias_kind":"pith_short_12","alias_value":"I3KEP3XELKBE","created_at":"2026-07-04T23:53:15.104141+00:00"},{"alias_kind":"pith_short_16","alias_value":"I3KEP3XELKBEWAPK","created_at":"2026-07-04T23:53:15.104141+00:00"},{"alias_kind":"pith_short_8","alias_value":"I3KEP3XE","created_at":"2026-07-04T23:53:15.104141+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.16229","citing_title":"TopView: Vectorising road users in a bird's eye view from uncalibrated street-level imagery with deep learning","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I3KEP3XELKBEWAPKZTJSL2HHVF","json":"https://pith.science/pith/I3KEP3XELKBEWAPKZTJSL2HHVF.json","graph_json":"https://pith.science/api/pith-number/I3KEP3XELKBEWAPKZTJSL2HHVF/graph.json","events_json":"https://pith.science/api/pith-number/I3KEP3XELKBEWAPKZTJSL2HHVF/events.json","paper":"https://pith.science/paper/I3KEP3XE"},"agent_actions":{"view_html":"https://pith.science/pith/I3KEP3XELKBEWAPKZTJSL2HHVF","download_json":"https://pith.science/pith/I3KEP3XELKBEWAPKZTJSL2HHVF.json","view_paper":"https://pith.science/paper/I3KEP3XE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.06038&json=true","fetch_graph":"https://pith.science/api/pith-number/I3KEP3XELKBEWAPKZTJSL2HHVF/graph.json","fetch_events":"https://pith.science/api/pith-number/I3KEP3XELKBEWAPKZTJSL2HHVF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I3KEP3XELKBEWAPKZTJSL2HHVF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I3KEP3XELKBEWAPKZTJSL2HHVF/action/storage_attestation","attest_author":"https://pith.science/pith/I3KEP3XELKBEWAPKZTJSL2HHVF/action/author_attestation","sign_citation":"https://pith.science/pith/I3KEP3XELKBEWAPKZTJSL2HHVF/action/citation_signature","submit_replication":"https://pith.science/pith/I3KEP3XELKBEWAPKZTJSL2HHVF/action/replication_record"}},"created_at":"2026-07-04T23:53:15.104141+00:00","updated_at":"2026-07-04T23:53:15.104141+00:00"}