{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HD53FBTOVPRWTYDW5VDVPKHX35","short_pith_number":"pith:HD53FBTO","schema_version":"1.0","canonical_sha256":"38fbb2866eabe369e076ed4757a8f7df7f6d42bc4ad2e1bf509faffebc701c5a","source":{"kind":"arxiv","id":"2404.10765","version":1},"attestation_state":"computed","paper":{"title":"RefFusion: Reference Adapted Diffusion Models for 3D Scene Inpainting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ashkan Mirzaei, David Acuna, Igor Gilitschenski, Jonathan Kelly, Riccardo de Lutio, Sanja Fidler, Seung Wook Kim, Zan Gojcic","submitted_at":"2024-04-16T17:50:02Z","abstract_excerpt":"Neural reconstruction approaches are rapidly emerging as the preferred representation for 3D scenes, but their limited editability is still posing a challenge. In this work, we propose an approach for 3D scene inpainting -- the task of coherently replacing parts of the reconstructed scene with desired content. Scene inpainting is an inherently ill-posed task as there exist many solutions that plausibly replace the missing content. A good inpainting method should therefore not only enable high-quality synthesis but also a high degree of control. Based on this observation, we focus on enabling e"},"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":"2404.10765","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T17:50:02Z","cross_cats_sorted":[],"title_canon_sha256":"4644f757c762e8bc49e330e1cfe1db21d735b2b4101f6b2d8f77b57708e6c7d4","abstract_canon_sha256":"44f0e77e3dfd3d7cd142782de2182638a67d5870ef12ac232c91a02e97ea4de5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:44.908648Z","signature_b64":"ao3kNxq8jtStzqxiaIPIFCIVw5lsnSRdMeqsNPYeMXVOahTI/Wx3Tpb5T9kipxy5blOXlhbGbbKlvsWFJBnoBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38fbb2866eabe369e076ed4757a8f7df7f6d42bc4ad2e1bf509faffebc701c5a","last_reissued_at":"2026-07-05T08:08:44.908186Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:44.908186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RefFusion: Reference Adapted Diffusion Models for 3D Scene Inpainting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ashkan Mirzaei, David Acuna, Igor Gilitschenski, Jonathan Kelly, Riccardo de Lutio, Sanja Fidler, Seung Wook Kim, Zan Gojcic","submitted_at":"2024-04-16T17:50:02Z","abstract_excerpt":"Neural reconstruction approaches are rapidly emerging as the preferred representation for 3D scenes, but their limited editability is still posing a challenge. In this work, we propose an approach for 3D scene inpainting -- the task of coherently replacing parts of the reconstructed scene with desired content. Scene inpainting is an inherently ill-posed task as there exist many solutions that plausibly replace the missing content. A good inpainting method should therefore not only enable high-quality synthesis but also a high degree of control. Based on this observation, we focus on enabling e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10765","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/2404.10765/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":"2404.10765","created_at":"2026-07-05T08:08:44.908235+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.10765v1","created_at":"2026-07-05T08:08:44.908235+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10765","created_at":"2026-07-05T08:08:44.908235+00:00"},{"alias_kind":"pith_short_12","alias_value":"HD53FBTOVPRW","created_at":"2026-07-05T08:08:44.908235+00:00"},{"alias_kind":"pith_short_16","alias_value":"HD53FBTOVPRWTYDW","created_at":"2026-07-05T08:08:44.908235+00:00"},{"alias_kind":"pith_short_8","alias_value":"HD53FBTO","created_at":"2026-07-05T08:08:44.908235+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.09977","citing_title":"A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation","ref_index":174,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09662","citing_title":"BEA-GS: BEyond RAdiance Supervision in 3DGS for Precise Object Extraction","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HD53FBTOVPRWTYDW5VDVPKHX35","json":"https://pith.science/pith/HD53FBTOVPRWTYDW5VDVPKHX35.json","graph_json":"https://pith.science/api/pith-number/HD53FBTOVPRWTYDW5VDVPKHX35/graph.json","events_json":"https://pith.science/api/pith-number/HD53FBTOVPRWTYDW5VDVPKHX35/events.json","paper":"https://pith.science/paper/HD53FBTO"},"agent_actions":{"view_html":"https://pith.science/pith/HD53FBTOVPRWTYDW5VDVPKHX35","download_json":"https://pith.science/pith/HD53FBTOVPRWTYDW5VDVPKHX35.json","view_paper":"https://pith.science/paper/HD53FBTO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.10765&json=true","fetch_graph":"https://pith.science/api/pith-number/HD53FBTOVPRWTYDW5VDVPKHX35/graph.json","fetch_events":"https://pith.science/api/pith-number/HD53FBTOVPRWTYDW5VDVPKHX35/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HD53FBTOVPRWTYDW5VDVPKHX35/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HD53FBTOVPRWTYDW5VDVPKHX35/action/storage_attestation","attest_author":"https://pith.science/pith/HD53FBTOVPRWTYDW5VDVPKHX35/action/author_attestation","sign_citation":"https://pith.science/pith/HD53FBTOVPRWTYDW5VDVPKHX35/action/citation_signature","submit_replication":"https://pith.science/pith/HD53FBTOVPRWTYDW5VDVPKHX35/action/replication_record"}},"created_at":"2026-07-05T08:08:44.908235+00:00","updated_at":"2026-07-05T08:08:44.908235+00:00"}