{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2XCNZJTRCAFL3XYSWNDPWVFYLG","short_pith_number":"pith:2XCNZJTR","schema_version":"1.0","canonical_sha256":"d5c4dca671100abddf12b346fb54b85984379078c7e44aeb86cc681b10820a73","source":{"kind":"arxiv","id":"2407.10592","version":1},"attestation_state":"computed","paper":{"title":"InsertDiffusion: Identity Preserving Visualization of Objects through a Training-Free Diffusion Architecture","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ioan Craciun, Jannik Wiese, Lars Mikelsons, Phillip Mueller","submitted_at":"2024-07-15T10:15:58Z","abstract_excerpt":"Recent advancements in image synthesis are fueled by the advent of large-scale diffusion models. Yet, integrating realistic object visualizations seamlessly into new or existing backgrounds without extensive training remains a challenge. This paper introduces InsertDiffusion, a novel, training-free diffusion architecture that efficiently embeds objects into images while preserving their structural and identity characteristics. Our approach utilizes off-the-shelf generative models and eliminates the need for fine-tuning, making it ideal for rapid and adaptable visualizations in product design 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":"2407.10592","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-15T10:15:58Z","cross_cats_sorted":[],"title_canon_sha256":"bf4931b48a4a28cc3bff3fed1d9ec6c65e6259c9d7c268e1cca2a8119129cfcc","abstract_canon_sha256":"99a9ae7696bf45f74ead82a9451e6189134a37cb383b7b1de69a8722e25c5f9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:01.583669Z","signature_b64":"dIwVmBuw79Hay1SbQJFXhhQJEEbcl1fyaCOXhKL4+ksJwHTQ3h4j7Jobac6TG59WMb+a94N4I3VhBeBRoVepDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5c4dca671100abddf12b346fb54b85984379078c7e44aeb86cc681b10820a73","last_reissued_at":"2026-07-05T08:44:01.583219Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:01.583219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InsertDiffusion: Identity Preserving Visualization of Objects through a Training-Free Diffusion Architecture","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ioan Craciun, Jannik Wiese, Lars Mikelsons, Phillip Mueller","submitted_at":"2024-07-15T10:15:58Z","abstract_excerpt":"Recent advancements in image synthesis are fueled by the advent of large-scale diffusion models. Yet, integrating realistic object visualizations seamlessly into new or existing backgrounds without extensive training remains a challenge. This paper introduces InsertDiffusion, a novel, training-free diffusion architecture that efficiently embeds objects into images while preserving their structural and identity characteristics. Our approach utilizes off-the-shelf generative models and eliminates the need for fine-tuning, making it ideal for rapid and adaptable visualizations in product design a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10592","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/2407.10592/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":"2407.10592","created_at":"2026-07-05T08:44:01.583283+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.10592v1","created_at":"2026-07-05T08:44:01.583283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10592","created_at":"2026-07-05T08:44:01.583283+00:00"},{"alias_kind":"pith_short_12","alias_value":"2XCNZJTRCAFL","created_at":"2026-07-05T08:44:01.583283+00:00"},{"alias_kind":"pith_short_16","alias_value":"2XCNZJTRCAFL3XYS","created_at":"2026-07-05T08:44:01.583283+00:00"},{"alias_kind":"pith_short_8","alias_value":"2XCNZJTR","created_at":"2026-07-05T08:44:01.583283+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16725","citing_title":"Masked Conditioning for Deep Generative Models","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2XCNZJTRCAFL3XYSWNDPWVFYLG","json":"https://pith.science/pith/2XCNZJTRCAFL3XYSWNDPWVFYLG.json","graph_json":"https://pith.science/api/pith-number/2XCNZJTRCAFL3XYSWNDPWVFYLG/graph.json","events_json":"https://pith.science/api/pith-number/2XCNZJTRCAFL3XYSWNDPWVFYLG/events.json","paper":"https://pith.science/paper/2XCNZJTR"},"agent_actions":{"view_html":"https://pith.science/pith/2XCNZJTRCAFL3XYSWNDPWVFYLG","download_json":"https://pith.science/pith/2XCNZJTRCAFL3XYSWNDPWVFYLG.json","view_paper":"https://pith.science/paper/2XCNZJTR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.10592&json=true","fetch_graph":"https://pith.science/api/pith-number/2XCNZJTRCAFL3XYSWNDPWVFYLG/graph.json","fetch_events":"https://pith.science/api/pith-number/2XCNZJTRCAFL3XYSWNDPWVFYLG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2XCNZJTRCAFL3XYSWNDPWVFYLG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2XCNZJTRCAFL3XYSWNDPWVFYLG/action/storage_attestation","attest_author":"https://pith.science/pith/2XCNZJTRCAFL3XYSWNDPWVFYLG/action/author_attestation","sign_citation":"https://pith.science/pith/2XCNZJTRCAFL3XYSWNDPWVFYLG/action/citation_signature","submit_replication":"https://pith.science/pith/2XCNZJTRCAFL3XYSWNDPWVFYLG/action/replication_record"}},"created_at":"2026-07-05T08:44:01.583283+00:00","updated_at":"2026-07-05T08:44:01.583283+00:00"}