{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KKZG7I3XIZBXTOBA26XRWR3AEU","short_pith_number":"pith:KKZG7I3X","schema_version":"1.0","canonical_sha256":"52b26fa377464379b820d7af1b4760252c1e017d1c36e14658cc14d8ef2860dc","source":{"kind":"arxiv","id":"1901.00212","version":3},"attestation_state":"computed","paper":{"title":"EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eric Ng, Faisal Z. Qureshi, Kamyar Nazeri, Mehran Ebrahimi, Tony Joseph","submitted_at":"2019-01-01T21:38:40Z","abstract_excerpt":"Over the last few years, deep learning techniques have yielded significant improvements in image inpainting. However, many of these techniques fail to reconstruct reasonable structures as they are commonly over-smoothed and/or blurry. This paper develops a new approach for image inpainting that does a better job of reproducing filled regions exhibiting fine details. We propose a two-stage adversarial model EdgeConnect that comprises of an edge generator followed by an image completion network. The edge generator hallucinates edges of the missing region (both regular and irregular) of the image"},"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":"1901.00212","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-01-01T21:38:40Z","cross_cats_sorted":[],"title_canon_sha256":"398f13016e63f79eff0714fbc923622e03bdc739a957e3315670146d3b3059f4","abstract_canon_sha256":"6b2da03a77f1116e715d56f397d276def22f1ba84929f47a8ed454ea8b264bab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:33.175545Z","signature_b64":"boXiJOVICRiqEarwPYKtjhKLrLXryON9vOidiDVtKZXHYrfb9BduAxr2oii31PbIhAc5QVx6FnmBwq6LbzyLAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52b26fa377464379b820d7af1b4760252c1e017d1c36e14658cc14d8ef2860dc","last_reissued_at":"2026-05-17T23:56:33.175052Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:33.175052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eric Ng, Faisal Z. Qureshi, Kamyar Nazeri, Mehran Ebrahimi, Tony Joseph","submitted_at":"2019-01-01T21:38:40Z","abstract_excerpt":"Over the last few years, deep learning techniques have yielded significant improvements in image inpainting. However, many of these techniques fail to reconstruct reasonable structures as they are commonly over-smoothed and/or blurry. This paper develops a new approach for image inpainting that does a better job of reproducing filled regions exhibiting fine details. We propose a two-stage adversarial model EdgeConnect that comprises of an edge generator followed by an image completion network. The edge generator hallucinates edges of the missing region (both regular and irregular) of the image"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.00212","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":""},"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":"1901.00212","created_at":"2026-05-17T23:56:33.175124+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.00212v3","created_at":"2026-05-17T23:56:33.175124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.00212","created_at":"2026-05-17T23:56:33.175124+00:00"},{"alias_kind":"pith_short_12","alias_value":"KKZG7I3XIZBX","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"KKZG7I3XIZBXTOBA","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"KKZG7I3X","created_at":"2026-05-18T12:33:21.387695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.16696","citing_title":"Face inpainting with Identity Preserving Latent Diffusion Models","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2112.10752","citing_title":"High-Resolution Image Synthesis with Latent Diffusion Models","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04904","citing_title":"Exploring Clustering Capability of Inpainting Model Embeddings for Pattern-based Individual Identification","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15723","citing_title":"Diffusion Autoencoder for Unsupervised Artifact Restoration in Handheld Fundus Images","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KKZG7I3XIZBXTOBA26XRWR3AEU","json":"https://pith.science/pith/KKZG7I3XIZBXTOBA26XRWR3AEU.json","graph_json":"https://pith.science/api/pith-number/KKZG7I3XIZBXTOBA26XRWR3AEU/graph.json","events_json":"https://pith.science/api/pith-number/KKZG7I3XIZBXTOBA26XRWR3AEU/events.json","paper":"https://pith.science/paper/KKZG7I3X"},"agent_actions":{"view_html":"https://pith.science/pith/KKZG7I3XIZBXTOBA26XRWR3AEU","download_json":"https://pith.science/pith/KKZG7I3XIZBXTOBA26XRWR3AEU.json","view_paper":"https://pith.science/paper/KKZG7I3X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.00212&json=true","fetch_graph":"https://pith.science/api/pith-number/KKZG7I3XIZBXTOBA26XRWR3AEU/graph.json","fetch_events":"https://pith.science/api/pith-number/KKZG7I3XIZBXTOBA26XRWR3AEU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KKZG7I3XIZBXTOBA26XRWR3AEU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KKZG7I3XIZBXTOBA26XRWR3AEU/action/storage_attestation","attest_author":"https://pith.science/pith/KKZG7I3XIZBXTOBA26XRWR3AEU/action/author_attestation","sign_citation":"https://pith.science/pith/KKZG7I3XIZBXTOBA26XRWR3AEU/action/citation_signature","submit_replication":"https://pith.science/pith/KKZG7I3XIZBXTOBA26XRWR3AEU/action/replication_record"}},"created_at":"2026-05-17T23:56:33.175124+00:00","updated_at":"2026-05-17T23:56:33.175124+00:00"}