{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5P3WXLCVIBB2OCKHAMYIGXIL5D","short_pith_number":"pith:5P3WXLCV","schema_version":"1.0","canonical_sha256":"ebf76bac554043a709470330835d0be8f8b9450f3f6e090c529da92c47bbe50c","source":{"kind":"arxiv","id":"2503.08677","version":2},"attestation_state":"computed","paper":{"title":"OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haitian Zheng, Jiebo Luo, Yongsheng Yu, Ziyun Zeng","submitted_at":"2025-03-11T17:55:27Z","abstract_excerpt":"Diffusion-based generative models have revolutionized object-oriented image editing, yet their deployment in realistic object removal and insertion remains hampered by challenges such as the intricate interplay of physical effects and insufficient paired training data. In this work, we introduce OmniPaint, a unified framework that re-conceptualizes object removal and insertion as interdependent processes rather than isolated tasks. Leveraging a pre-trained diffusion prior along with a progressive training pipeline comprising initial paired sample optimization and subsequent large-scale unpaire"},"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":"2503.08677","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-11T17:55:27Z","cross_cats_sorted":[],"title_canon_sha256":"e69d04dad0bb288504e3794b4b4159944194fcfa18f89cff4296b8d313db0541","abstract_canon_sha256":"8af746e101fe06b67218194b06fab4132651fd3f3f96e357679c2132cebb9d17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:38.186125Z","signature_b64":"Vk/BnGwegQDf6z5qL3RMf46bdA4nLAWu4e2PAW1CRS5b239L/klFRxMvNuV1CunuCMee6op1l+9ycNaRPcIyAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebf76bac554043a709470330835d0be8f8b9450f3f6e090c529da92c47bbe50c","last_reissued_at":"2026-07-05T10:29:38.185238Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:38.185238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haitian Zheng, Jiebo Luo, Yongsheng Yu, Ziyun Zeng","submitted_at":"2025-03-11T17:55:27Z","abstract_excerpt":"Diffusion-based generative models have revolutionized object-oriented image editing, yet their deployment in realistic object removal and insertion remains hampered by challenges such as the intricate interplay of physical effects and insufficient paired training data. In this work, we introduce OmniPaint, a unified framework that re-conceptualizes object removal and insertion as interdependent processes rather than isolated tasks. Leveraging a pre-trained diffusion prior along with a progressive training pipeline comprising initial paired sample optimization and subsequent large-scale unpaire"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08677","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/2503.08677/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":"2503.08677","created_at":"2026-07-05T10:29:38.185362+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.08677v2","created_at":"2026-07-05T10:29:38.185362+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08677","created_at":"2026-07-05T10:29:38.185362+00:00"},{"alias_kind":"pith_short_12","alias_value":"5P3WXLCVIBB2","created_at":"2026-07-05T10:29:38.185362+00:00"},{"alias_kind":"pith_short_16","alias_value":"5P3WXLCVIBB2OCKH","created_at":"2026-07-05T10:29:38.185362+00:00"},{"alias_kind":"pith_short_8","alias_value":"5P3WXLCV","created_at":"2026-07-05T10:29:38.185362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15921","citing_title":"AdaEraser: Training-Free Object Removal via Adaptive Attention Suppression","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18652","citing_title":"MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08836","citing_title":"CatalogStitch: Dimension-Aware and Occlusion-Preserving Object Compositing for Catalog Image Generation","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5P3WXLCVIBB2OCKHAMYIGXIL5D","json":"https://pith.science/pith/5P3WXLCVIBB2OCKHAMYIGXIL5D.json","graph_json":"https://pith.science/api/pith-number/5P3WXLCVIBB2OCKHAMYIGXIL5D/graph.json","events_json":"https://pith.science/api/pith-number/5P3WXLCVIBB2OCKHAMYIGXIL5D/events.json","paper":"https://pith.science/paper/5P3WXLCV"},"agent_actions":{"view_html":"https://pith.science/pith/5P3WXLCVIBB2OCKHAMYIGXIL5D","download_json":"https://pith.science/pith/5P3WXLCVIBB2OCKHAMYIGXIL5D.json","view_paper":"https://pith.science/paper/5P3WXLCV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.08677&json=true","fetch_graph":"https://pith.science/api/pith-number/5P3WXLCVIBB2OCKHAMYIGXIL5D/graph.json","fetch_events":"https://pith.science/api/pith-number/5P3WXLCVIBB2OCKHAMYIGXIL5D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5P3WXLCVIBB2OCKHAMYIGXIL5D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5P3WXLCVIBB2OCKHAMYIGXIL5D/action/storage_attestation","attest_author":"https://pith.science/pith/5P3WXLCVIBB2OCKHAMYIGXIL5D/action/author_attestation","sign_citation":"https://pith.science/pith/5P3WXLCVIBB2OCKHAMYIGXIL5D/action/citation_signature","submit_replication":"https://pith.science/pith/5P3WXLCVIBB2OCKHAMYIGXIL5D/action/replication_record"}},"created_at":"2026-07-05T10:29:38.185362+00:00","updated_at":"2026-07-05T10:29:38.185362+00:00"}