{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:QOUPSQRYU5OBQPVH2SLWC5TLEL","short_pith_number":"pith:QOUPSQRY","schema_version":"1.0","canonical_sha256":"83a8f94238a75c183ea7d49761766b22c2b44341bcffa64dc6d0d6111a15e13e","source":{"kind":"arxiv","id":"1607.07539","version":3},"attestation_state":"computed","paper":{"title":"Semantic Image Inpainting with Deep Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander G. Schwing, Chen Chen, Mark Hasegawa-Johnson, Minh N. Do, Raymond A. Yeh, Teck Yian Lim","submitted_at":"2016-07-26T04:52:48Z","abstract_excerpt":"Semantic image inpainting is a challenging task where large missing regions have to be filled based on the available visual data. Existing methods which extract information from only a single image generally produce unsatisfactory results due to the lack of high level context. In this paper, we propose a novel method for semantic image inpainting, which generates the missing content by conditioning on the available data. Given a trained generative model, we search for the closest encoding of the corrupted image in the latent image manifold using our context and prior losses. This encoding is t"},"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":"1607.07539","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-07-26T04:52:48Z","cross_cats_sorted":[],"title_canon_sha256":"be91e48d73eaf3def14745e0a1dbe940b1ba01c0f3de4952b9e369f685011c37","abstract_canon_sha256":"a8f30d238034f4d1e0986507813b4b5e1a4529e4eb2087e1f28d03d97e8ece87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:24.223599Z","signature_b64":"gMKng6Eko3q6U82s2o/hkR0LrIeKlGuLOVo0tEwKB1QhqHqIkmHPoal0S81mM1bd4zyCdqf1+PXwkSoZ8ea0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83a8f94238a75c183ea7d49761766b22c2b44341bcffa64dc6d0d6111a15e13e","last_reissued_at":"2026-05-18T00:40:24.222757Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:24.222757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic Image Inpainting with Deep Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander G. Schwing, Chen Chen, Mark Hasegawa-Johnson, Minh N. Do, Raymond A. Yeh, Teck Yian Lim","submitted_at":"2016-07-26T04:52:48Z","abstract_excerpt":"Semantic image inpainting is a challenging task where large missing regions have to be filled based on the available visual data. Existing methods which extract information from only a single image generally produce unsatisfactory results due to the lack of high level context. In this paper, we propose a novel method for semantic image inpainting, which generates the missing content by conditioning on the available data. Given a trained generative model, we search for the closest encoding of the corrupted image in the latent image manifold using our context and prior losses. This encoding is t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.07539","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":"1607.07539","created_at":"2026-05-18T00:40:24.222863+00:00"},{"alias_kind":"arxiv_version","alias_value":"1607.07539v3","created_at":"2026-05-18T00:40:24.222863+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.07539","created_at":"2026-05-18T00:40:24.222863+00:00"},{"alias_kind":"pith_short_12","alias_value":"QOUPSQRYU5OB","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_16","alias_value":"QOUPSQRYU5OBQPVH","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_8","alias_value":"QOUPSQRY","created_at":"2026-05-18T12:30:39.010887+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.02987","citing_title":"RED: A ReRAM-based Deconvolution Accelerator","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QOUPSQRYU5OBQPVH2SLWC5TLEL","json":"https://pith.science/pith/QOUPSQRYU5OBQPVH2SLWC5TLEL.json","graph_json":"https://pith.science/api/pith-number/QOUPSQRYU5OBQPVH2SLWC5TLEL/graph.json","events_json":"https://pith.science/api/pith-number/QOUPSQRYU5OBQPVH2SLWC5TLEL/events.json","paper":"https://pith.science/paper/QOUPSQRY"},"agent_actions":{"view_html":"https://pith.science/pith/QOUPSQRYU5OBQPVH2SLWC5TLEL","download_json":"https://pith.science/pith/QOUPSQRYU5OBQPVH2SLWC5TLEL.json","view_paper":"https://pith.science/paper/QOUPSQRY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1607.07539&json=true","fetch_graph":"https://pith.science/api/pith-number/QOUPSQRYU5OBQPVH2SLWC5TLEL/graph.json","fetch_events":"https://pith.science/api/pith-number/QOUPSQRYU5OBQPVH2SLWC5TLEL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QOUPSQRYU5OBQPVH2SLWC5TLEL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QOUPSQRYU5OBQPVH2SLWC5TLEL/action/storage_attestation","attest_author":"https://pith.science/pith/QOUPSQRYU5OBQPVH2SLWC5TLEL/action/author_attestation","sign_citation":"https://pith.science/pith/QOUPSQRYU5OBQPVH2SLWC5TLEL/action/citation_signature","submit_replication":"https://pith.science/pith/QOUPSQRYU5OBQPVH2SLWC5TLEL/action/replication_record"}},"created_at":"2026-05-18T00:40:24.222863+00:00","updated_at":"2026-05-18T00:40:24.222863+00:00"}