{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NCFSCULLRH7RZJS7H6BC7RQHHX","short_pith_number":"pith:NCFSCULL","schema_version":"1.0","canonical_sha256":"688b21516b89ff1ca65f3f822fc6073dfc155c6c0d020b3cc4a5b6928d8ebb90","source":{"kind":"arxiv","id":"2404.14403","version":2},"attestation_state":"computed","paper":{"title":"GeoDiffuser: Geometry-Based Image Editing with Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jeroen Vanbaar, Jie Min, Kapil Katyal, Rahul Sajnani, Srinath Sridhar","submitted_at":"2024-04-22T17:58:36Z","abstract_excerpt":"The success of image generative models has enabled us to build methods that can edit images based on text or other user input. However, these methods are bespoke, imprecise, require additional information, or are limited to only 2D image edits. We present GeoDiffuser, a zero-shot optimization-based method that unifies common 2D and 3D image-based object editing capabilities into a single method. Our key insight is to view image editing operations as geometric transformations. We show that these transformations can be directly incorporated into the attention layers in diffusion models to implic"},"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":"2404.14403","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-22T17:58:36Z","cross_cats_sorted":[],"title_canon_sha256":"71b499435f7bc11082eaac5944fed850cca8f3013cafb3dc029f768ef8948061","abstract_canon_sha256":"5476d9dfcd254dceae9390f4f0e86fea7c893fa41ba74896042b669b467268fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:56.519296Z","signature_b64":"1+/3x1EcBZdlAQjWvidw7YYYMkAkbRDcT8eNrpxlaiYrA+sj88cIHydMHSLOcTB/QiR776dyLUDTYhX7bxUxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"688b21516b89ff1ca65f3f822fc6073dfc155c6c0d020b3cc4a5b6928d8ebb90","last_reissued_at":"2026-07-05T09:55:56.518735Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:56.518735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GeoDiffuser: Geometry-Based Image Editing with Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jeroen Vanbaar, Jie Min, Kapil Katyal, Rahul Sajnani, Srinath Sridhar","submitted_at":"2024-04-22T17:58:36Z","abstract_excerpt":"The success of image generative models has enabled us to build methods that can edit images based on text or other user input. However, these methods are bespoke, imprecise, require additional information, or are limited to only 2D image edits. We present GeoDiffuser, a zero-shot optimization-based method that unifies common 2D and 3D image-based object editing capabilities into a single method. Our key insight is to view image editing operations as geometric transformations. We show that these transformations can be directly incorporated into the attention layers in diffusion models to implic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.14403","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/2404.14403/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":"2404.14403","created_at":"2026-07-05T09:55:56.518802+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.14403v2","created_at":"2026-07-05T09:55:56.518802+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.14403","created_at":"2026-07-05T09:55:56.518802+00:00"},{"alias_kind":"pith_short_12","alias_value":"NCFSCULLRH7R","created_at":"2026-07-05T09:55:56.518802+00:00"},{"alias_kind":"pith_short_16","alias_value":"NCFSCULLRH7RZJS7","created_at":"2026-07-05T09:55:56.518802+00:00"},{"alias_kind":"pith_short_8","alias_value":"NCFSCULL","created_at":"2026-07-05T09:55:56.518802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.19840","citing_title":"GenHSI: Controllable Generation of Human-Scene Interaction Videos","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NCFSCULLRH7RZJS7H6BC7RQHHX","json":"https://pith.science/pith/NCFSCULLRH7RZJS7H6BC7RQHHX.json","graph_json":"https://pith.science/api/pith-number/NCFSCULLRH7RZJS7H6BC7RQHHX/graph.json","events_json":"https://pith.science/api/pith-number/NCFSCULLRH7RZJS7H6BC7RQHHX/events.json","paper":"https://pith.science/paper/NCFSCULL"},"agent_actions":{"view_html":"https://pith.science/pith/NCFSCULLRH7RZJS7H6BC7RQHHX","download_json":"https://pith.science/pith/NCFSCULLRH7RZJS7H6BC7RQHHX.json","view_paper":"https://pith.science/paper/NCFSCULL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.14403&json=true","fetch_graph":"https://pith.science/api/pith-number/NCFSCULLRH7RZJS7H6BC7RQHHX/graph.json","fetch_events":"https://pith.science/api/pith-number/NCFSCULLRH7RZJS7H6BC7RQHHX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NCFSCULLRH7RZJS7H6BC7RQHHX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NCFSCULLRH7RZJS7H6BC7RQHHX/action/storage_attestation","attest_author":"https://pith.science/pith/NCFSCULLRH7RZJS7H6BC7RQHHX/action/author_attestation","sign_citation":"https://pith.science/pith/NCFSCULLRH7RZJS7H6BC7RQHHX/action/citation_signature","submit_replication":"https://pith.science/pith/NCFSCULLRH7RZJS7H6BC7RQHHX/action/replication_record"}},"created_at":"2026-07-05T09:55:56.518802+00:00","updated_at":"2026-07-05T09:55:56.518802+00:00"}