{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XXA3EGE2EPMZZ46SYSYVXGGPFS","short_pith_number":"pith:XXA3EGE2","schema_version":"1.0","canonical_sha256":"bdc1b2189a23d99cf3d2c4b15b98cf2c963167bc51549d7e1c2a6dcc9d8bfaa3","source":{"kind":"arxiv","id":"2402.04625","version":1},"attestation_state":"computed","paper":{"title":"Noise Map Guidance: Inversion with Spatial Context for Real Image Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hansam Cho, Jonghyun Lee, Seoung Bum Kim, Tae-Hyun Oh, Yonghyun Jeong","submitted_at":"2024-02-07T07:16:12Z","abstract_excerpt":"Text-guided diffusion models have become a popular tool in image synthesis, known for producing high-quality and diverse images. However, their application to editing real images often encounters hurdles primarily due to the text condition deteriorating the reconstruction quality and subsequently affecting editing fidelity. Null-text Inversion (NTI) has made strides in this area, but it fails to capture spatial context and requires computationally intensive per-timestep optimization. Addressing these challenges, we present Noise Map Guidance (NMG), an inversion method rich in a spatial context"},"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":"2402.04625","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-07T07:16:12Z","cross_cats_sorted":[],"title_canon_sha256":"927c7d0aa53b60d487c27e93820f1aa59fab178d95eed3eeaec4145ffc4984dc","abstract_canon_sha256":"484a7fa1acd1b18e4e71b5c48664cae26bb34c35aa0277e5215b68e7093c7a86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:29.672454Z","signature_b64":"huJE3WDB0cj5G4W0UJ48RmgbTsYp7pGFyXgdLgajn2RZhUyOChFM/UYN34RiqBNc8Sawc+ksGHb4WUapCZJ7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdc1b2189a23d99cf3d2c4b15b98cf2c963167bc51549d7e1c2a6dcc9d8bfaa3","last_reissued_at":"2026-07-05T07:42:29.672013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:29.672013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Noise Map Guidance: Inversion with Spatial Context for Real Image Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hansam Cho, Jonghyun Lee, Seoung Bum Kim, Tae-Hyun Oh, Yonghyun Jeong","submitted_at":"2024-02-07T07:16:12Z","abstract_excerpt":"Text-guided diffusion models have become a popular tool in image synthesis, known for producing high-quality and diverse images. However, their application to editing real images often encounters hurdles primarily due to the text condition deteriorating the reconstruction quality and subsequently affecting editing fidelity. Null-text Inversion (NTI) has made strides in this area, but it fails to capture spatial context and requires computationally intensive per-timestep optimization. Addressing these challenges, we present Noise Map Guidance (NMG), an inversion method rich in a spatial context"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04625","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/2402.04625/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":"2402.04625","created_at":"2026-07-05T07:42:29.672065+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.04625v1","created_at":"2026-07-05T07:42:29.672065+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04625","created_at":"2026-07-05T07:42:29.672065+00:00"},{"alias_kind":"pith_short_12","alias_value":"XXA3EGE2EPMZ","created_at":"2026-07-05T07:42:29.672065+00:00"},{"alias_kind":"pith_short_16","alias_value":"XXA3EGE2EPMZZ46S","created_at":"2026-07-05T07:42:29.672065+00:00"},{"alias_kind":"pith_short_8","alias_value":"XXA3EGE2","created_at":"2026-07-05T07:42:29.672065+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.22171","citing_title":"An Empirical Study of Validating Synthetic Data for Text-Based Person Retrieval","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XXA3EGE2EPMZZ46SYSYVXGGPFS","json":"https://pith.science/pith/XXA3EGE2EPMZZ46SYSYVXGGPFS.json","graph_json":"https://pith.science/api/pith-number/XXA3EGE2EPMZZ46SYSYVXGGPFS/graph.json","events_json":"https://pith.science/api/pith-number/XXA3EGE2EPMZZ46SYSYVXGGPFS/events.json","paper":"https://pith.science/paper/XXA3EGE2"},"agent_actions":{"view_html":"https://pith.science/pith/XXA3EGE2EPMZZ46SYSYVXGGPFS","download_json":"https://pith.science/pith/XXA3EGE2EPMZZ46SYSYVXGGPFS.json","view_paper":"https://pith.science/paper/XXA3EGE2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.04625&json=true","fetch_graph":"https://pith.science/api/pith-number/XXA3EGE2EPMZZ46SYSYVXGGPFS/graph.json","fetch_events":"https://pith.science/api/pith-number/XXA3EGE2EPMZZ46SYSYVXGGPFS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XXA3EGE2EPMZZ46SYSYVXGGPFS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XXA3EGE2EPMZZ46SYSYVXGGPFS/action/storage_attestation","attest_author":"https://pith.science/pith/XXA3EGE2EPMZZ46SYSYVXGGPFS/action/author_attestation","sign_citation":"https://pith.science/pith/XXA3EGE2EPMZZ46SYSYVXGGPFS/action/citation_signature","submit_replication":"https://pith.science/pith/XXA3EGE2EPMZZ46SYSYVXGGPFS/action/replication_record"}},"created_at":"2026-07-05T07:42:29.672065+00:00","updated_at":"2026-07-05T07:42:29.672065+00:00"}