{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7T3M6O22ND66F2L7A5YNKTDSTG","short_pith_number":"pith:7T3M6O22","schema_version":"1.0","canonical_sha256":"fcf6cf3b5a68fde2e97f0770d54c7299b1e83c05b4dc0be1a8126d7e40d4af66","source":{"kind":"arxiv","id":"2104.01431","version":1},"attestation_state":"computed","paper":{"title":"Aggregated Contextual Transformations for High-Resolution Image Inpainting","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baining Guo, Hongyang Chao, Jianlong Fu, Yanhong Zeng","submitted_at":"2021-04-03T15:50:17Z","abstract_excerpt":"State-of-the-art image inpainting approaches can suffer from generating distorted structures and blurry textures in high-resolution images (e.g., 512x512). The challenges mainly drive from (1) image content reasoning from distant contexts, and (2) fine-grained texture synthesis for a large missing region. To overcome these two challenges, we propose an enhanced GAN-based model, named Aggregated COntextual-Transformation GAN (AOT-GAN), for high-resolution image inpainting. Specifically, to enhance context reasoning, we construct the generator of AOT-GAN by stacking multiple layers of a proposed"},"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":"2104.01431","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-03T15:50:17Z","cross_cats_sorted":[],"title_canon_sha256":"e069a8f3a1b64eae2b1ce33d2d578b8eff454e4b10dab79bbd0fc021afc2ec44","abstract_canon_sha256":"af550975667c1cbeb6a6e580ea3ac9874926e4bf4186e59658b8eebb65b2875a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:07.463377Z","signature_b64":"VunMaT5qrqOgZcJj/a20/nKEFpkbFAQ3asSvLxEsoyvCWGZXxHaPzHA4Ty+TQNcMEb9ob6MBVu5c3/QkiJcQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcf6cf3b5a68fde2e97f0770d54c7299b1e83c05b4dc0be1a8126d7e40d4af66","last_reissued_at":"2026-07-05T09:26:07.462158Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:07.462158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aggregated Contextual Transformations for High-Resolution Image Inpainting","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baining Guo, Hongyang Chao, Jianlong Fu, Yanhong Zeng","submitted_at":"2021-04-03T15:50:17Z","abstract_excerpt":"State-of-the-art image inpainting approaches can suffer from generating distorted structures and blurry textures in high-resolution images (e.g., 512x512). The challenges mainly drive from (1) image content reasoning from distant contexts, and (2) fine-grained texture synthesis for a large missing region. To overcome these two challenges, we propose an enhanced GAN-based model, named Aggregated COntextual-Transformation GAN (AOT-GAN), for high-resolution image inpainting. Specifically, to enhance context reasoning, we construct the generator of AOT-GAN by stacking multiple layers of a proposed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01431","kind":"arxiv","version":1},"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/2104.01431/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":"2104.01431","created_at":"2026-07-05T09:26:07.462871+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.01431v1","created_at":"2026-07-05T09:26:07.462871+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01431","created_at":"2026-07-05T09:26:07.462871+00:00"},{"alias_kind":"pith_short_12","alias_value":"7T3M6O22ND66","created_at":"2026-07-05T09:26:07.462871+00:00"},{"alias_kind":"pith_short_16","alias_value":"7T3M6O22ND66F2L7","created_at":"2026-07-05T09:26:07.462871+00:00"},{"alias_kind":"pith_short_8","alias_value":"7T3M6O22","created_at":"2026-07-05T09:26:07.462871+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.21834","citing_title":"PrefPaint: Enhancing Medical Image Inpainting through Expert Human Feedback","ref_index":36,"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":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7T3M6O22ND66F2L7A5YNKTDSTG","json":"https://pith.science/pith/7T3M6O22ND66F2L7A5YNKTDSTG.json","graph_json":"https://pith.science/api/pith-number/7T3M6O22ND66F2L7A5YNKTDSTG/graph.json","events_json":"https://pith.science/api/pith-number/7T3M6O22ND66F2L7A5YNKTDSTG/events.json","paper":"https://pith.science/paper/7T3M6O22"},"agent_actions":{"view_html":"https://pith.science/pith/7T3M6O22ND66F2L7A5YNKTDSTG","download_json":"https://pith.science/pith/7T3M6O22ND66F2L7A5YNKTDSTG.json","view_paper":"https://pith.science/paper/7T3M6O22","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.01431&json=true","fetch_graph":"https://pith.science/api/pith-number/7T3M6O22ND66F2L7A5YNKTDSTG/graph.json","fetch_events":"https://pith.science/api/pith-number/7T3M6O22ND66F2L7A5YNKTDSTG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7T3M6O22ND66F2L7A5YNKTDSTG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7T3M6O22ND66F2L7A5YNKTDSTG/action/storage_attestation","attest_author":"https://pith.science/pith/7T3M6O22ND66F2L7A5YNKTDSTG/action/author_attestation","sign_citation":"https://pith.science/pith/7T3M6O22ND66F2L7A5YNKTDSTG/action/citation_signature","submit_replication":"https://pith.science/pith/7T3M6O22ND66F2L7A5YNKTDSTG/action/replication_record"}},"created_at":"2026-07-05T09:26:07.462871+00:00","updated_at":"2026-07-05T09:26:07.462871+00:00"}