{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6UDKV44MD5DZFV5OODTGG6A5WJ","short_pith_number":"pith:6UDKV44M","schema_version":"1.0","canonical_sha256":"f506aaf38c1f4792d7ae70e663781db261c2d5919970d82bb6b83bdcce904ed6","source":{"kind":"arxiv","id":"2203.11105","version":2},"attestation_state":"computed","paper":{"title":"High-fidelity GAN Inversion with Padding Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiapeng Zhu, Qingyan Bai, Weihao Xia, Yinghao Xu, Yujiu Yang, Yujun Shen","submitted_at":"2022-03-21T16:32:12Z","abstract_excerpt":"Inverting a Generative Adversarial Network (GAN) facilitates a wide range of image editing tasks using pre-trained generators. Existing methods typically employ the latent space of GANs as the inversion space yet observe the insufficient recovery of spatial details. In this work, we propose to involve the padding space of the generator to complement the latent space with spatial information. Concretely, we replace the constant padding (e.g., usually zeros) used in convolution layers with some instance-aware coefficients. In this way, the inductive bias assumed in the pre-trained model can be a"},"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":"2203.11105","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-21T16:32:12Z","cross_cats_sorted":[],"title_canon_sha256":"9506d746b143d089aee6263227b75b3d7d9ed5c3be8a978de6ae4dc1add90329","abstract_canon_sha256":"048e08739f62084169d7d92495d8283bf2d490d34bf8d71f0470ad7a3bd7d619"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:44:00.618622Z","signature_b64":"LHERScHFee+a3KtJnrGkDkq4K63GmlnV6+c19haUIXdDBeV/iU7oH6BEiaNetRDy+oy2005JP95+n2VTblsKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f506aaf38c1f4792d7ae70e663781db261c2d5919970d82bb6b83bdcce904ed6","last_reissued_at":"2026-07-05T04:44:00.618108Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:44:00.618108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-fidelity GAN Inversion with Padding Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiapeng Zhu, Qingyan Bai, Weihao Xia, Yinghao Xu, Yujiu Yang, Yujun Shen","submitted_at":"2022-03-21T16:32:12Z","abstract_excerpt":"Inverting a Generative Adversarial Network (GAN) facilitates a wide range of image editing tasks using pre-trained generators. Existing methods typically employ the latent space of GANs as the inversion space yet observe the insufficient recovery of spatial details. In this work, we propose to involve the padding space of the generator to complement the latent space with spatial information. Concretely, we replace the constant padding (e.g., usually zeros) used in convolution layers with some instance-aware coefficients. In this way, the inductive bias assumed in the pre-trained model can be a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.11105","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/2203.11105/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":"2203.11105","created_at":"2026-07-05T04:44:00.618170+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.11105v2","created_at":"2026-07-05T04:44:00.618170+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.11105","created_at":"2026-07-05T04:44:00.618170+00:00"},{"alias_kind":"pith_short_12","alias_value":"6UDKV44MD5DZ","created_at":"2026-07-05T04:44:00.618170+00:00"},{"alias_kind":"pith_short_16","alias_value":"6UDKV44MD5DZFV5O","created_at":"2026-07-05T04:44:00.618170+00:00"},{"alias_kind":"pith_short_8","alias_value":"6UDKV44M","created_at":"2026-07-05T04:44:00.618170+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/6UDKV44MD5DZFV5OODTGG6A5WJ","json":"https://pith.science/pith/6UDKV44MD5DZFV5OODTGG6A5WJ.json","graph_json":"https://pith.science/api/pith-number/6UDKV44MD5DZFV5OODTGG6A5WJ/graph.json","events_json":"https://pith.science/api/pith-number/6UDKV44MD5DZFV5OODTGG6A5WJ/events.json","paper":"https://pith.science/paper/6UDKV44M"},"agent_actions":{"view_html":"https://pith.science/pith/6UDKV44MD5DZFV5OODTGG6A5WJ","download_json":"https://pith.science/pith/6UDKV44MD5DZFV5OODTGG6A5WJ.json","view_paper":"https://pith.science/paper/6UDKV44M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.11105&json=true","fetch_graph":"https://pith.science/api/pith-number/6UDKV44MD5DZFV5OODTGG6A5WJ/graph.json","fetch_events":"https://pith.science/api/pith-number/6UDKV44MD5DZFV5OODTGG6A5WJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6UDKV44MD5DZFV5OODTGG6A5WJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6UDKV44MD5DZFV5OODTGG6A5WJ/action/storage_attestation","attest_author":"https://pith.science/pith/6UDKV44MD5DZFV5OODTGG6A5WJ/action/author_attestation","sign_citation":"https://pith.science/pith/6UDKV44MD5DZFV5OODTGG6A5WJ/action/citation_signature","submit_replication":"https://pith.science/pith/6UDKV44MD5DZFV5OODTGG6A5WJ/action/replication_record"}},"created_at":"2026-07-05T04:44:00.618170+00:00","updated_at":"2026-07-05T04:44:00.618170+00:00"}