{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:E6UINPRIX7UTZO7D7TOHE76NB3","short_pith_number":"pith:E6UINPRI","schema_version":"1.0","canonical_sha256":"27a886be28bfe93cbbe3fcdc727fcd0ec8a3d88b974818490993e475de2201eb","source":{"kind":"arxiv","id":"2206.08357","version":1},"attestation_state":"computed","paper":{"title":"Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Gaurav Parmar, Jingwan Lu, Jun-Yan Zhu, Krishna Kumar Singh, Richard Zhang, Yijun Li","submitted_at":"2022-06-16T17:57:49Z","abstract_excerpt":"Existing GAN inversion and editing methods work well for aligned objects with a clean background, such as portraits and animal faces, but often struggle for more difficult categories with complex scene layouts and object occlusions, such as cars, animals, and outdoor images. We propose a new method to invert and edit such complex images in the latent space of GANs, such as StyleGAN2. Our key idea is to explore inversion with a collection of layers, spatially adapting the inversion process to the difficulty of the image. We learn to predict the \"invertibility\" of different image segments and pr"},"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":"2206.08357","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-16T17:57:49Z","cross_cats_sorted":["cs.GR","cs.LG"],"title_canon_sha256":"c1ef363596b3e82f77fd3dc8c086c9ca7f6a19ddaa9c379f2209ed88c2abda0c","abstract_canon_sha256":"7bda739e2f3cdfeb9a7068457e598afd78d2d54c56a5867aec42c6eb81086f99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:24.747478Z","signature_b64":"cKClmtS47CAvruuRj1edJtUh7tb5wG0YNZHQcKlx9FQ8V2O4/KIGWalmS1vsi+xFVAnNGGdOgC8Rd0P5Wuv7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27a886be28bfe93cbbe3fcdc727fcd0ec8a3d88b974818490993e475de2201eb","last_reissued_at":"2026-07-05T04:32:24.746945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:24.746945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Gaurav Parmar, Jingwan Lu, Jun-Yan Zhu, Krishna Kumar Singh, Richard Zhang, Yijun Li","submitted_at":"2022-06-16T17:57:49Z","abstract_excerpt":"Existing GAN inversion and editing methods work well for aligned objects with a clean background, such as portraits and animal faces, but often struggle for more difficult categories with complex scene layouts and object occlusions, such as cars, animals, and outdoor images. We propose a new method to invert and edit such complex images in the latent space of GANs, such as StyleGAN2. Our key idea is to explore inversion with a collection of layers, spatially adapting the inversion process to the difficulty of the image. We learn to predict the \"invertibility\" of different image segments and pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08357","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/2206.08357/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":"2206.08357","created_at":"2026-07-05T04:32:24.747009+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.08357v1","created_at":"2026-07-05T04:32:24.747009+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08357","created_at":"2026-07-05T04:32:24.747009+00:00"},{"alias_kind":"pith_short_12","alias_value":"E6UINPRIX7UT","created_at":"2026-07-05T04:32:24.747009+00:00"},{"alias_kind":"pith_short_16","alias_value":"E6UINPRIX7UTZO7D","created_at":"2026-07-05T04:32:24.747009+00:00"},{"alias_kind":"pith_short_8","alias_value":"E6UINPRI","created_at":"2026-07-05T04:32:24.747009+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/E6UINPRIX7UTZO7D7TOHE76NB3","json":"https://pith.science/pith/E6UINPRIX7UTZO7D7TOHE76NB3.json","graph_json":"https://pith.science/api/pith-number/E6UINPRIX7UTZO7D7TOHE76NB3/graph.json","events_json":"https://pith.science/api/pith-number/E6UINPRIX7UTZO7D7TOHE76NB3/events.json","paper":"https://pith.science/paper/E6UINPRI"},"agent_actions":{"view_html":"https://pith.science/pith/E6UINPRIX7UTZO7D7TOHE76NB3","download_json":"https://pith.science/pith/E6UINPRIX7UTZO7D7TOHE76NB3.json","view_paper":"https://pith.science/paper/E6UINPRI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.08357&json=true","fetch_graph":"https://pith.science/api/pith-number/E6UINPRIX7UTZO7D7TOHE76NB3/graph.json","fetch_events":"https://pith.science/api/pith-number/E6UINPRIX7UTZO7D7TOHE76NB3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E6UINPRIX7UTZO7D7TOHE76NB3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E6UINPRIX7UTZO7D7TOHE76NB3/action/storage_attestation","attest_author":"https://pith.science/pith/E6UINPRIX7UTZO7D7TOHE76NB3/action/author_attestation","sign_citation":"https://pith.science/pith/E6UINPRIX7UTZO7D7TOHE76NB3/action/citation_signature","submit_replication":"https://pith.science/pith/E6UINPRIX7UTZO7D7TOHE76NB3/action/replication_record"}},"created_at":"2026-07-05T04:32:24.747009+00:00","updated_at":"2026-07-05T04:32:24.747009+00:00"}