{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z3WAOVIW5JQBJEMHST6E2V5VTZ","short_pith_number":"pith:Z3WAOVIW","schema_version":"1.0","canonical_sha256":"ceec075516ea6014918794fc4d57b59e411ed082074fb01a4a9ebafce7e8584d","source":{"kind":"arxiv","id":"2412.03558","version":3},"attestation_state":"computed","paper":{"title":"MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ding Liang, Lu Sheng, Xihui Liu, Xingqiao An, Yangguang Li, Yan-Pei Cao, Yuan-Chen Guo, Yunhan Yang, Zehuan Huang, Zi-Xin Zou","submitted_at":"2024-12-04T18:52:40Z","abstract_excerpt":"This paper introduces MIDI, a novel paradigm for compositional 3D scene generation from a single image. Unlike existing methods that rely on reconstruction or retrieval techniques or recent approaches that employ multi-stage object-by-object generation, MIDI extends pre-trained image-to-3D object generation models to multi-instance diffusion models, enabling the simultaneous generation of multiple 3D instances with accurate spatial relationships and high generalizability. At its core, MIDI incorporates a novel multi-instance attention mechanism, that effectively captures inter-object interacti"},"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":"2412.03558","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T18:52:40Z","cross_cats_sorted":[],"title_canon_sha256":"26cc0ec4c2326f662f1c43320ac202e6244b883bfd520ec1eb0e1fc4b408e371","abstract_canon_sha256":"ab93f4276786e9d3702f518d47951ec97fa934e99c4ff3bd090710a09cad5086"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:25.656380Z","signature_b64":"Wv7M38O5Z1o2mXC1TN1bI/TvBlDGE8tJ6Qkd1mkd74J5u6bFBAtyjysdoE6N0lY/MBeA53cDtAUrywBBYqnyDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ceec075516ea6014918794fc4d57b59e411ed082074fb01a4a9ebafce7e8584d","last_reissued_at":"2026-07-05T11:38:25.655669Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:25.655669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ding Liang, Lu Sheng, Xihui Liu, Xingqiao An, Yangguang Li, Yan-Pei Cao, Yuan-Chen Guo, Yunhan Yang, Zehuan Huang, Zi-Xin Zou","submitted_at":"2024-12-04T18:52:40Z","abstract_excerpt":"This paper introduces MIDI, a novel paradigm for compositional 3D scene generation from a single image. Unlike existing methods that rely on reconstruction or retrieval techniques or recent approaches that employ multi-stage object-by-object generation, MIDI extends pre-trained image-to-3D object generation models to multi-instance diffusion models, enabling the simultaneous generation of multiple 3D instances with accurate spatial relationships and high generalizability. At its core, MIDI incorporates a novel multi-instance attention mechanism, that effectively captures inter-object interacti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03558","kind":"arxiv","version":3},"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/2412.03558/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":"2412.03558","created_at":"2026-07-05T11:38:25.655762+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.03558v3","created_at":"2026-07-05T11:38:25.655762+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03558","created_at":"2026-07-05T11:38:25.655762+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z3WAOVIW5JQB","created_at":"2026-07-05T11:38:25.655762+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z3WAOVIW5JQBJEMH","created_at":"2026-07-05T11:38:25.655762+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z3WAOVIW","created_at":"2026-07-05T11:38:25.655762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28060","citing_title":"ReScene: Structured Indoor Scene Reconstruction from Multi-View Captures","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16137","citing_title":"STABLE: Simulation-Ready Tabletop Layout Generation via a Semantics-Physics Dual System","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2509.10813","citing_title":"InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z3WAOVIW5JQBJEMHST6E2V5VTZ","json":"https://pith.science/pith/Z3WAOVIW5JQBJEMHST6E2V5VTZ.json","graph_json":"https://pith.science/api/pith-number/Z3WAOVIW5JQBJEMHST6E2V5VTZ/graph.json","events_json":"https://pith.science/api/pith-number/Z3WAOVIW5JQBJEMHST6E2V5VTZ/events.json","paper":"https://pith.science/paper/Z3WAOVIW"},"agent_actions":{"view_html":"https://pith.science/pith/Z3WAOVIW5JQBJEMHST6E2V5VTZ","download_json":"https://pith.science/pith/Z3WAOVIW5JQBJEMHST6E2V5VTZ.json","view_paper":"https://pith.science/paper/Z3WAOVIW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.03558&json=true","fetch_graph":"https://pith.science/api/pith-number/Z3WAOVIW5JQBJEMHST6E2V5VTZ/graph.json","fetch_events":"https://pith.science/api/pith-number/Z3WAOVIW5JQBJEMHST6E2V5VTZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z3WAOVIW5JQBJEMHST6E2V5VTZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z3WAOVIW5JQBJEMHST6E2V5VTZ/action/storage_attestation","attest_author":"https://pith.science/pith/Z3WAOVIW5JQBJEMHST6E2V5VTZ/action/author_attestation","sign_citation":"https://pith.science/pith/Z3WAOVIW5JQBJEMHST6E2V5VTZ/action/citation_signature","submit_replication":"https://pith.science/pith/Z3WAOVIW5JQBJEMHST6E2V5VTZ/action/replication_record"}},"created_at":"2026-07-05T11:38:25.655762+00:00","updated_at":"2026-07-05T11:38:25.655762+00:00"}