{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NDPKGLXHYXG5RR6WS7DA62YMR4","short_pith_number":"pith:NDPKGLXH","schema_version":"1.0","canonical_sha256":"68dea32ee7c5cdd8c7d697c60f6b0c8f0d72e2899e18369d17e06bb17d09a88f","source":{"kind":"arxiv","id":"1909.00968","version":3},"attestation_state":"computed","paper":{"title":"Image Inpainting with Learnable Bidirectional Attention Maps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaohao Xie, Chao Li, Errui Ding, Ming-Ming Cheng, Shaohui Liu, Shilei Wen, Wangmeng Zuo, Xiao Liu","submitted_at":"2019-09-03T06:18:40Z","abstract_excerpt":"Most convolutional network (CNN)-based inpainting methods adopt standard convolution to indistinguishably treat valid pixels and holes, making them limited in handling irregular holes and more likely to generate inpainting results with color discrepancy and blurriness. Partial convolution has been suggested to address this issue, but it adopts handcrafted feature re-normalization, and only considers forward mask-updating. In this paper, we present a learnable attention map module for learning feature renormalization and mask-updating in an end-to-end manner, which is effective in adapting to i"},"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":"1909.00968","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-03T06:18:40Z","cross_cats_sorted":[],"title_canon_sha256":"5e742b739a2a0a54305570b6220ccef6f60d8ab5982f7ad7fc742edeff86ce3f","abstract_canon_sha256":"5fbd38545a30fddb6e85db370eacdaa1a1f7ebcae89bf4960d84a3c4b1b1e388"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:28.965421Z","signature_b64":"Ol914syBrgR8a4+kKuqOc37y09oP83mBM8PjE87pE8ditk2+pnI44Ak2lVCFjeFjYNFmEe8/inYuO32UNsvmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68dea32ee7c5cdd8c7d697c60f6b0c8f0d72e2899e18369d17e06bb17d09a88f","last_reissued_at":"2026-07-05T00:02:28.964868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:28.964868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Image Inpainting with Learnable Bidirectional Attention Maps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaohao Xie, Chao Li, Errui Ding, Ming-Ming Cheng, Shaohui Liu, Shilei Wen, Wangmeng Zuo, Xiao Liu","submitted_at":"2019-09-03T06:18:40Z","abstract_excerpt":"Most convolutional network (CNN)-based inpainting methods adopt standard convolution to indistinguishably treat valid pixels and holes, making them limited in handling irregular holes and more likely to generate inpainting results with color discrepancy and blurriness. Partial convolution has been suggested to address this issue, but it adopts handcrafted feature re-normalization, and only considers forward mask-updating. In this paper, we present a learnable attention map module for learning feature renormalization and mask-updating in an end-to-end manner, which is effective in adapting to i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.00968","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/1909.00968/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":"1909.00968","created_at":"2026-07-05T00:02:28.964925+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.00968v3","created_at":"2026-07-05T00:02:28.964925+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.00968","created_at":"2026-07-05T00:02:28.964925+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDPKGLXHYXG5","created_at":"2026-07-05T00:02:28.964925+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDPKGLXHYXG5RR6W","created_at":"2026-07-05T00:02:28.964925+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDPKGLXH","created_at":"2026-07-05T00:02:28.964925+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/NDPKGLXHYXG5RR6WS7DA62YMR4","json":"https://pith.science/pith/NDPKGLXHYXG5RR6WS7DA62YMR4.json","graph_json":"https://pith.science/api/pith-number/NDPKGLXHYXG5RR6WS7DA62YMR4/graph.json","events_json":"https://pith.science/api/pith-number/NDPKGLXHYXG5RR6WS7DA62YMR4/events.json","paper":"https://pith.science/paper/NDPKGLXH"},"agent_actions":{"view_html":"https://pith.science/pith/NDPKGLXHYXG5RR6WS7DA62YMR4","download_json":"https://pith.science/pith/NDPKGLXHYXG5RR6WS7DA62YMR4.json","view_paper":"https://pith.science/paper/NDPKGLXH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.00968&json=true","fetch_graph":"https://pith.science/api/pith-number/NDPKGLXHYXG5RR6WS7DA62YMR4/graph.json","fetch_events":"https://pith.science/api/pith-number/NDPKGLXHYXG5RR6WS7DA62YMR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDPKGLXHYXG5RR6WS7DA62YMR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDPKGLXHYXG5RR6WS7DA62YMR4/action/storage_attestation","attest_author":"https://pith.science/pith/NDPKGLXHYXG5RR6WS7DA62YMR4/action/author_attestation","sign_citation":"https://pith.science/pith/NDPKGLXHYXG5RR6WS7DA62YMR4/action/citation_signature","submit_replication":"https://pith.science/pith/NDPKGLXHYXG5RR6WS7DA62YMR4/action/replication_record"}},"created_at":"2026-07-05T00:02:28.964925+00:00","updated_at":"2026-07-05T00:02:28.964925+00:00"}