{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UK6B6JCB3DOFYWKMCKXPP6PTTV","short_pith_number":"pith:UK6B6JCB","schema_version":"1.0","canonical_sha256":"a2bc1f2441d8dc5c594c12aef7f9f39d69a7a543ac191703d4fe9cd50d8c728f","source":{"kind":"arxiv","id":"2407.17850","version":1},"attestation_state":"computed","paper":{"title":"FlexiEdit: Frequency-Aware Latent Refinement for Enhanced Non-Rigid Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang D. Yoo, Gwanhyeong Koo, Ji Woo Hong, Sunjae Yoon","submitted_at":"2024-07-25T08:07:40Z","abstract_excerpt":"Current image editing methods primarily utilize DDIM Inversion, employing a two-branch diffusion approach to preserve the attributes and layout of the original image. However, these methods encounter challenges with non-rigid edits, which involve altering the image's layout or structure. Our comprehensive analysis reveals that the high-frequency components of DDIM latent, crucial for retaining the original image's key features and layout, significantly contribute to these limitations. Addressing this, we introduce FlexiEdit, which enhances fidelity to input text prompts by refining DDIM latent"},"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":"2407.17850","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-25T08:07:40Z","cross_cats_sorted":[],"title_canon_sha256":"9d7bb13d7b2aa15425baa90073dc494cc92b6d23d35906f016421f6c37547e52","abstract_canon_sha256":"9ebf3720db6c1699ce6d60708f29d3d6bef633f534e3ba372cd87a34f68236f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:22.515330Z","signature_b64":"L9JLXA1LeCzBoSsekHfH2KIM5npM7QxT5HcAdHrfN3QnlM3VyVPCLOOTP1gWabvFaohg8Qmj2eneElL08LQ+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2bc1f2441d8dc5c594c12aef7f9f39d69a7a543ac191703d4fe9cd50d8c728f","last_reissued_at":"2026-07-05T08:48:22.514918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:22.514918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlexiEdit: Frequency-Aware Latent Refinement for Enhanced Non-Rigid Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang D. Yoo, Gwanhyeong Koo, Ji Woo Hong, Sunjae Yoon","submitted_at":"2024-07-25T08:07:40Z","abstract_excerpt":"Current image editing methods primarily utilize DDIM Inversion, employing a two-branch diffusion approach to preserve the attributes and layout of the original image. However, these methods encounter challenges with non-rigid edits, which involve altering the image's layout or structure. Our comprehensive analysis reveals that the high-frequency components of DDIM latent, crucial for retaining the original image's key features and layout, significantly contribute to these limitations. Addressing this, we introduce FlexiEdit, which enhances fidelity to input text prompts by refining DDIM latent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17850","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/2407.17850/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":"2407.17850","created_at":"2026-07-05T08:48:22.514975+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.17850v1","created_at":"2026-07-05T08:48:22.514975+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17850","created_at":"2026-07-05T08:48:22.514975+00:00"},{"alias_kind":"pith_short_12","alias_value":"UK6B6JCB3DOF","created_at":"2026-07-05T08:48:22.514975+00:00"},{"alias_kind":"pith_short_16","alias_value":"UK6B6JCB3DOFYWKM","created_at":"2026-07-05T08:48:22.514975+00:00"},{"alias_kind":"pith_short_8","alias_value":"UK6B6JCB","created_at":"2026-07-05T08:48:22.514975+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.21090","citing_title":"Q-Align: Alleviating Attention Leakage in Zero-Shot Appearance Transfer via Query-Query Alignment","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UK6B6JCB3DOFYWKMCKXPP6PTTV","json":"https://pith.science/pith/UK6B6JCB3DOFYWKMCKXPP6PTTV.json","graph_json":"https://pith.science/api/pith-number/UK6B6JCB3DOFYWKMCKXPP6PTTV/graph.json","events_json":"https://pith.science/api/pith-number/UK6B6JCB3DOFYWKMCKXPP6PTTV/events.json","paper":"https://pith.science/paper/UK6B6JCB"},"agent_actions":{"view_html":"https://pith.science/pith/UK6B6JCB3DOFYWKMCKXPP6PTTV","download_json":"https://pith.science/pith/UK6B6JCB3DOFYWKMCKXPP6PTTV.json","view_paper":"https://pith.science/paper/UK6B6JCB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.17850&json=true","fetch_graph":"https://pith.science/api/pith-number/UK6B6JCB3DOFYWKMCKXPP6PTTV/graph.json","fetch_events":"https://pith.science/api/pith-number/UK6B6JCB3DOFYWKMCKXPP6PTTV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UK6B6JCB3DOFYWKMCKXPP6PTTV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UK6B6JCB3DOFYWKMCKXPP6PTTV/action/storage_attestation","attest_author":"https://pith.science/pith/UK6B6JCB3DOFYWKMCKXPP6PTTV/action/author_attestation","sign_citation":"https://pith.science/pith/UK6B6JCB3DOFYWKMCKXPP6PTTV/action/citation_signature","submit_replication":"https://pith.science/pith/UK6B6JCB3DOFYWKMCKXPP6PTTV/action/replication_record"}},"created_at":"2026-07-05T08:48:22.514975+00:00","updated_at":"2026-07-05T08:48:22.514975+00:00"}