{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WEGIL6WGALF4H7JCJYOHAEKXMZ","short_pith_number":"pith:WEGIL6WG","schema_version":"1.0","canonical_sha256":"b10c85fac602cbc3fd224e1c7011576657724bad500dcdeb07b54eed31bbf10a","source":{"kind":"arxiv","id":"1909.06043","version":3},"attestation_state":"computed","paper":{"title":"End-to-End Learnable Geometric Vision by Backpropagating PnP Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alvaro Parra, Bo Chen, Jiewei Cao, Nan Li, Tat-Jun Chin","submitted_at":"2019-09-13T05:45:25Z","abstract_excerpt":"Deep networks excel in learning patterns from large amounts of data. On the other hand, many geometric vision tasks are specified as optimization problems. To seamlessly combine deep learning and geometric vision, it is vital to perform learning and geometric optimization end-to-end. Towards this aim, we present BPnP, a novel network module that backpropagates gradients through a Perspective-n-Points (PnP) solver to guide parameter updates of a neural network. Based on implicit differentiation, we show that the gradients of a \"self-contained\" PnP solver can be derived accurately and efficientl"},"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":"1909.06043","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-13T05:45:25Z","cross_cats_sorted":[],"title_canon_sha256":"84d80ef635934eaf69cb51d28b08b00d47bd38b5278180ab1110446fbc267534","abstract_canon_sha256":"9efd9fe32a61133ea7d27f261895bb465b558aa2bfdcfa9bd9b5f3041e8ed754"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:47:59.077690Z","signature_b64":"FAa5dRAB7lxNf0Pow82DxlXrJpNuaDtEelQ3CmeHSr/fYQLhAeaEeAZu3t2Gar9NQ7AR10/na7/mhBGWLazPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b10c85fac602cbc3fd224e1c7011576657724bad500dcdeb07b54eed31bbf10a","last_reissued_at":"2026-07-05T00:47:59.077304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:47:59.077304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Learnable Geometric Vision by Backpropagating PnP Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alvaro Parra, Bo Chen, Jiewei Cao, Nan Li, Tat-Jun Chin","submitted_at":"2019-09-13T05:45:25Z","abstract_excerpt":"Deep networks excel in learning patterns from large amounts of data. On the other hand, many geometric vision tasks are specified as optimization problems. To seamlessly combine deep learning and geometric vision, it is vital to perform learning and geometric optimization end-to-end. Towards this aim, we present BPnP, a novel network module that backpropagates gradients through a Perspective-n-Points (PnP) solver to guide parameter updates of a neural network. Based on implicit differentiation, we show that the gradients of a \"self-contained\" PnP solver can be derived accurately and efficientl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.06043","kind":"arxiv","version":3},"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/1909.06043/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":"1909.06043","created_at":"2026-07-05T00:47:59.077381+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.06043v3","created_at":"2026-07-05T00:47:59.077381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.06043","created_at":"2026-07-05T00:47:59.077381+00:00"},{"alias_kind":"pith_short_12","alias_value":"WEGIL6WGALF4","created_at":"2026-07-05T00:47:59.077381+00:00"},{"alias_kind":"pith_short_16","alias_value":"WEGIL6WGALF4H7JC","created_at":"2026-07-05T00:47:59.077381+00:00"},{"alias_kind":"pith_short_8","alias_value":"WEGIL6WG","created_at":"2026-07-05T00:47:59.077381+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WEGIL6WGALF4H7JCJYOHAEKXMZ","json":"https://pith.science/pith/WEGIL6WGALF4H7JCJYOHAEKXMZ.json","graph_json":"https://pith.science/api/pith-number/WEGIL6WGALF4H7JCJYOHAEKXMZ/graph.json","events_json":"https://pith.science/api/pith-number/WEGIL6WGALF4H7JCJYOHAEKXMZ/events.json","paper":"https://pith.science/paper/WEGIL6WG"},"agent_actions":{"view_html":"https://pith.science/pith/WEGIL6WGALF4H7JCJYOHAEKXMZ","download_json":"https://pith.science/pith/WEGIL6WGALF4H7JCJYOHAEKXMZ.json","view_paper":"https://pith.science/paper/WEGIL6WG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.06043&json=true","fetch_graph":"https://pith.science/api/pith-number/WEGIL6WGALF4H7JCJYOHAEKXMZ/graph.json","fetch_events":"https://pith.science/api/pith-number/WEGIL6WGALF4H7JCJYOHAEKXMZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WEGIL6WGALF4H7JCJYOHAEKXMZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WEGIL6WGALF4H7JCJYOHAEKXMZ/action/storage_attestation","attest_author":"https://pith.science/pith/WEGIL6WGALF4H7JCJYOHAEKXMZ/action/author_attestation","sign_citation":"https://pith.science/pith/WEGIL6WGALF4H7JCJYOHAEKXMZ/action/citation_signature","submit_replication":"https://pith.science/pith/WEGIL6WGALF4H7JCJYOHAEKXMZ/action/replication_record"}},"created_at":"2026-07-05T00:47:59.077381+00:00","updated_at":"2026-07-05T00:47:59.077381+00:00"}