{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Q2OOETBFEWUMQ7TINIQIEKOORA","short_pith_number":"pith:Q2OOETBF","schema_version":"1.0","canonical_sha256":"869ce24c2525a8c87e686a208229ce8833f30ee12bd1cd6ab44afd8efcc2a307","source":{"kind":"arxiv","id":"2110.12942","version":2},"attestation_state":"computed","paper":{"title":"DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Feng, Houqiang Li, Jiajun Deng, Wengang Zhou, Yuechen Wang","submitted_at":"2021-10-25T13:27:10Z","abstract_excerpt":"In this work, we propose a new framework, called Document Image Transformer (DocTr), to address the issue of geometry and illumination distortion of the document images. Specifically, DocTr consists of a geometric unwarping transformer and an illumination correction transformer. By setting a set of learned query embedding, the geometric unwarping transformer captures the global context of the document image by self-attention mechanism and decodes the pixel-wise displacement solution to correct the geometric distortion. After geometric unwarping, our illumination correction transformer further "},"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":"2110.12942","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-25T13:27:10Z","cross_cats_sorted":[],"title_canon_sha256":"0bf2ebdced4155593c899681e6a0b816a3c5f9d6dc911f67a65303c24aa99a7c","abstract_canon_sha256":"d49bcecc365dfec2ecfa83c393e91dc4908b2b8b1ff65caa50849f2f77e22a62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:25.806137Z","signature_b64":"JHgvGKQDL3QMoTlagXdPFZLZUZ/JMhLbd+ZzjTOYDkdXkrMymOPBjrOJEBLQnx7IHVVRSG2mAcyT4bLVfgKWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"869ce24c2525a8c87e686a208229ce8833f30ee12bd1cd6ab44afd8efcc2a307","last_reissued_at":"2026-07-05T05:04:25.805748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:25.805748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Feng, Houqiang Li, Jiajun Deng, Wengang Zhou, Yuechen Wang","submitted_at":"2021-10-25T13:27:10Z","abstract_excerpt":"In this work, we propose a new framework, called Document Image Transformer (DocTr), to address the issue of geometry and illumination distortion of the document images. Specifically, DocTr consists of a geometric unwarping transformer and an illumination correction transformer. By setting a set of learned query embedding, the geometric unwarping transformer captures the global context of the document image by self-attention mechanism and decodes the pixel-wise displacement solution to correct the geometric distortion. After geometric unwarping, our illumination correction transformer further "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12942","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/2110.12942/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":"2110.12942","created_at":"2026-07-05T05:04:25.805809+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.12942v2","created_at":"2026-07-05T05:04:25.805809+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12942","created_at":"2026-07-05T05:04:25.805809+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q2OOETBFEWUM","created_at":"2026-07-05T05:04:25.805809+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q2OOETBFEWUMQ7TI","created_at":"2026-07-05T05:04:25.805809+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q2OOETBF","created_at":"2026-07-05T05:04:25.805809+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.03615","citing_title":"E-ARMOR: Edge case Assessment and Review of Multilingual Optical Character Recognition","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q2OOETBFEWUMQ7TINIQIEKOORA","json":"https://pith.science/pith/Q2OOETBFEWUMQ7TINIQIEKOORA.json","graph_json":"https://pith.science/api/pith-number/Q2OOETBFEWUMQ7TINIQIEKOORA/graph.json","events_json":"https://pith.science/api/pith-number/Q2OOETBFEWUMQ7TINIQIEKOORA/events.json","paper":"https://pith.science/paper/Q2OOETBF"},"agent_actions":{"view_html":"https://pith.science/pith/Q2OOETBFEWUMQ7TINIQIEKOORA","download_json":"https://pith.science/pith/Q2OOETBFEWUMQ7TINIQIEKOORA.json","view_paper":"https://pith.science/paper/Q2OOETBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.12942&json=true","fetch_graph":"https://pith.science/api/pith-number/Q2OOETBFEWUMQ7TINIQIEKOORA/graph.json","fetch_events":"https://pith.science/api/pith-number/Q2OOETBFEWUMQ7TINIQIEKOORA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q2OOETBFEWUMQ7TINIQIEKOORA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q2OOETBFEWUMQ7TINIQIEKOORA/action/storage_attestation","attest_author":"https://pith.science/pith/Q2OOETBFEWUMQ7TINIQIEKOORA/action/author_attestation","sign_citation":"https://pith.science/pith/Q2OOETBFEWUMQ7TINIQIEKOORA/action/citation_signature","submit_replication":"https://pith.science/pith/Q2OOETBFEWUMQ7TINIQIEKOORA/action/replication_record"}},"created_at":"2026-07-05T05:04:25.805809+00:00","updated_at":"2026-07-05T05:04:25.805809+00:00"}