{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:32K2A6VJHAR5Z2WIRBTJZ6B7ZV","short_pith_number":"pith:32K2A6VJ","schema_version":"1.0","canonical_sha256":"de95a07aa93823dceac888669cf83fcd59d0178a3dc6b6f97b8508757232668b","source":{"kind":"arxiv","id":"1806.03589","version":2},"attestation_state":"computed","paper":{"title":"Free-Form Image Inpainting with Gated Convolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiahui Yu, Jimei Yang, Thomas Huang, Xiaohui Shen, Xin Lu, Zhe Lin","submitted_at":"2018-06-10T05:51:32Z","abstract_excerpt":"We present a generative image inpainting system to complete images with free-form mask and guidance. The system is based on gated convolutions learned from millions of images without additional labelling efforts. The proposed gated convolution solves the issue of vanilla convolution that treats all input pixels as valid ones, generalizes partial convolution by providing a learnable dynamic feature selection mechanism for each channel at each spatial location across all layers. Moreover, as free-form masks may appear anywhere in images with any shape, global and local GANs designed for a single"},"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":"1806.03589","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-10T05:51:32Z","cross_cats_sorted":["cs.GR","cs.LG"],"title_canon_sha256":"8fd3ee1f49fd0f06d4002270022b9d72a2cbf6c985b30a39b8f6ad624511ded4","abstract_canon_sha256":"d1e466073dde1dd3ccf3bf5424ee90ce16c7fd767c54c99feb04d9809b2be7d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:13:36.302465Z","signature_b64":"UYl+lluspEQJt2Cfnv9bDiePaaAhw0OCpHqfi+ztUQitFNPEmDzpmefZU5sgHGEu7rmY0w5Rb3USnHn7Jt7bBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de95a07aa93823dceac888669cf83fcd59d0178a3dc6b6f97b8508757232668b","last_reissued_at":"2026-07-05T00:13:36.302037Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:13:36.302037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Free-Form Image Inpainting with Gated Convolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiahui Yu, Jimei Yang, Thomas Huang, Xiaohui Shen, Xin Lu, Zhe Lin","submitted_at":"2018-06-10T05:51:32Z","abstract_excerpt":"We present a generative image inpainting system to complete images with free-form mask and guidance. The system is based on gated convolutions learned from millions of images without additional labelling efforts. The proposed gated convolution solves the issue of vanilla convolution that treats all input pixels as valid ones, generalizes partial convolution by providing a learnable dynamic feature selection mechanism for each channel at each spatial location across all layers. Moreover, as free-form masks may appear anywhere in images with any shape, global and local GANs designed for a single"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03589","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/1806.03589/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":"1806.03589","created_at":"2026-07-05T00:13:36.302093+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.03589v2","created_at":"2026-07-05T00:13:36.302093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03589","created_at":"2026-07-05T00:13:36.302093+00:00"},{"alias_kind":"pith_short_12","alias_value":"32K2A6VJHAR5","created_at":"2026-07-05T00:13:36.302093+00:00"},{"alias_kind":"pith_short_16","alias_value":"32K2A6VJHAR5Z2WI","created_at":"2026-07-05T00:13:36.302093+00:00"},{"alias_kind":"pith_short_8","alias_value":"32K2A6VJ","created_at":"2026-07-05T00:13:36.302093+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1907.05740","citing_title":"Gated-SCNN: Gated Shape CNNs for Semantic Segmentation","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"1907.06296","citing_title":"Perceptually Motivated Method for Image Inpainting Comparison","ref_index":30,"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":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/32K2A6VJHAR5Z2WIRBTJZ6B7ZV","json":"https://pith.science/pith/32K2A6VJHAR5Z2WIRBTJZ6B7ZV.json","graph_json":"https://pith.science/api/pith-number/32K2A6VJHAR5Z2WIRBTJZ6B7ZV/graph.json","events_json":"https://pith.science/api/pith-number/32K2A6VJHAR5Z2WIRBTJZ6B7ZV/events.json","paper":"https://pith.science/paper/32K2A6VJ"},"agent_actions":{"view_html":"https://pith.science/pith/32K2A6VJHAR5Z2WIRBTJZ6B7ZV","download_json":"https://pith.science/pith/32K2A6VJHAR5Z2WIRBTJZ6B7ZV.json","view_paper":"https://pith.science/paper/32K2A6VJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.03589&json=true","fetch_graph":"https://pith.science/api/pith-number/32K2A6VJHAR5Z2WIRBTJZ6B7ZV/graph.json","fetch_events":"https://pith.science/api/pith-number/32K2A6VJHAR5Z2WIRBTJZ6B7ZV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/32K2A6VJHAR5Z2WIRBTJZ6B7ZV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/32K2A6VJHAR5Z2WIRBTJZ6B7ZV/action/storage_attestation","attest_author":"https://pith.science/pith/32K2A6VJHAR5Z2WIRBTJZ6B7ZV/action/author_attestation","sign_citation":"https://pith.science/pith/32K2A6VJHAR5Z2WIRBTJZ6B7ZV/action/citation_signature","submit_replication":"https://pith.science/pith/32K2A6VJHAR5Z2WIRBTJZ6B7ZV/action/replication_record"}},"created_at":"2026-07-05T00:13:36.302093+00:00","updated_at":"2026-07-05T00:13:36.302093+00:00"}