{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:QEKWAPEQBX2VP26ONO3EKJIYHN","short_pith_number":"pith:QEKWAPEQ","schema_version":"1.0","canonical_sha256":"8115603c900df557ebce6bb64525183b45bdf7c48ab23455c1fc3a5a80238ad0","source":{"kind":"arxiv","id":"1811.10247","version":2},"attestation_state":"computed","paper":{"title":"MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinglu Wang, Yan Lu, Zengyi Qin","submitted_at":"2018-11-26T09:36:40Z","abstract_excerpt":"Detecting and localizing objects in the real 3D space, which plays a crucial role in scene understanding, is particularly challenging given only a single RGB image due to the geometric information loss during imagery projection. We propose MonoGRNet for the amodal 3D object detection from a monocular RGB image via geometric reasoning in both the observed 2D projection and the unobserved depth dimension. MonoGRNet is a single, unified network composed of four task-specific subnetworks, responsible for 2D object detection, instance depth estimation (IDE), 3D localization and local corner regress"},"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":"1811.10247","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-26T09:36:40Z","cross_cats_sorted":[],"title_canon_sha256":"424518f176fca3d848ce6eba6166e76b48441e50a376617fdf2c809f0b5fc579","abstract_canon_sha256":"985c61606edd18a40565d9705996e536b7773fff2dcb77856ee7a945ae87da3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:51:27.041355Z","signature_b64":"Vce/cEj0HpTkREl2Ryo7tXHUC6UOVpxZiXeEFCoWYk+PdU2VXvHBUgy+au0FeIUseFA90XxUgWOjH1z/bwh/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8115603c900df557ebce6bb64525183b45bdf7c48ab23455c1fc3a5a80238ad0","last_reissued_at":"2026-07-05T00:51:27.040972Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:51:27.040972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinglu Wang, Yan Lu, Zengyi Qin","submitted_at":"2018-11-26T09:36:40Z","abstract_excerpt":"Detecting and localizing objects in the real 3D space, which plays a crucial role in scene understanding, is particularly challenging given only a single RGB image due to the geometric information loss during imagery projection. We propose MonoGRNet for the amodal 3D object detection from a monocular RGB image via geometric reasoning in both the observed 2D projection and the unobserved depth dimension. MonoGRNet is a single, unified network composed of four task-specific subnetworks, responsible for 2D object detection, instance depth estimation (IDE), 3D localization and local corner regress"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10247","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/1811.10247/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":"1811.10247","created_at":"2026-07-05T00:51:27.041036+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.10247v2","created_at":"2026-07-05T00:51:27.041036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10247","created_at":"2026-07-05T00:51:27.041036+00:00"},{"alias_kind":"pith_short_12","alias_value":"QEKWAPEQBX2V","created_at":"2026-07-05T00:51:27.041036+00:00"},{"alias_kind":"pith_short_16","alias_value":"QEKWAPEQBX2VP26O","created_at":"2026-07-05T00:51:27.041036+00:00"},{"alias_kind":"pith_short_8","alias_value":"QEKWAPEQ","created_at":"2026-07-05T00:51:27.041036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06687","citing_title":"StixelNExT++: Lightweight Monocular Scene Segmentation and Representation for Collective Perception","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QEKWAPEQBX2VP26ONO3EKJIYHN","json":"https://pith.science/pith/QEKWAPEQBX2VP26ONO3EKJIYHN.json","graph_json":"https://pith.science/api/pith-number/QEKWAPEQBX2VP26ONO3EKJIYHN/graph.json","events_json":"https://pith.science/api/pith-number/QEKWAPEQBX2VP26ONO3EKJIYHN/events.json","paper":"https://pith.science/paper/QEKWAPEQ"},"agent_actions":{"view_html":"https://pith.science/pith/QEKWAPEQBX2VP26ONO3EKJIYHN","download_json":"https://pith.science/pith/QEKWAPEQBX2VP26ONO3EKJIYHN.json","view_paper":"https://pith.science/paper/QEKWAPEQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.10247&json=true","fetch_graph":"https://pith.science/api/pith-number/QEKWAPEQBX2VP26ONO3EKJIYHN/graph.json","fetch_events":"https://pith.science/api/pith-number/QEKWAPEQBX2VP26ONO3EKJIYHN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QEKWAPEQBX2VP26ONO3EKJIYHN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QEKWAPEQBX2VP26ONO3EKJIYHN/action/storage_attestation","attest_author":"https://pith.science/pith/QEKWAPEQBX2VP26ONO3EKJIYHN/action/author_attestation","sign_citation":"https://pith.science/pith/QEKWAPEQBX2VP26ONO3EKJIYHN/action/citation_signature","submit_replication":"https://pith.science/pith/QEKWAPEQBX2VP26ONO3EKJIYHN/action/replication_record"}},"created_at":"2026-07-05T00:51:27.041036+00:00","updated_at":"2026-07-05T00:51:27.041036+00:00"}