{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3PM4N7EYECOLGRE5X2FIPATUEH","short_pith_number":"pith:3PM4N7EY","schema_version":"1.0","canonical_sha256":"dbd9c6fc98209cb3449dbe8a87827421f3c973c3b39df05fd1f81184da215d47","source":{"kind":"arxiv","id":"2305.02743","version":2},"attestation_state":"computed","paper":{"title":"Incremental 3D Semantic Scene Graph Prediction from RGB Sequences","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Federico Tombari, Keisuke Tateno, Nassir Navab, Shun-Cheng Wu","submitted_at":"2023-05-04T11:32:16Z","abstract_excerpt":"3D semantic scene graphs are a powerful holistic representation as they describe the individual objects and depict the relation between them. They are compact high-level graphs that enable many tasks requiring scene reasoning. In real-world settings, existing 3D estimation methods produce robust predictions that mostly rely on dense inputs. In this work, we propose a real-time framework that incrementally builds a consistent 3D semantic scene graph of a scene given an RGB image sequence. Our method consists of a novel incremental entity estimation pipeline and a scene graph prediction network."},"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":"2305.02743","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-04T11:32:16Z","cross_cats_sorted":[],"title_canon_sha256":"4ca063b84c316ff06a80cdd233b084f4dcc5e2b2e2dfadb70825a40fc1e0b3b2","abstract_canon_sha256":"f80c37402e1d1e8cff0fc9526bfe7603e2766fc1a0697a85dfc0ba5cfb20ee7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:07:39.801464Z","signature_b64":"N3sVVzKxUojYkFeg4id56VIk1gCCv0jHVR88BPTuN+yiHQJdU+1O8gTJq1fV8JYZVOqFEOWPMO/hRmp70HwCAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbd9c6fc98209cb3449dbe8a87827421f3c973c3b39df05fd1f81184da215d47","last_reissued_at":"2026-07-05T06:07:39.801016Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:07:39.801016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incremental 3D Semantic Scene Graph Prediction from RGB Sequences","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Federico Tombari, Keisuke Tateno, Nassir Navab, Shun-Cheng Wu","submitted_at":"2023-05-04T11:32:16Z","abstract_excerpt":"3D semantic scene graphs are a powerful holistic representation as they describe the individual objects and depict the relation between them. They are compact high-level graphs that enable many tasks requiring scene reasoning. In real-world settings, existing 3D estimation methods produce robust predictions that mostly rely on dense inputs. In this work, we propose a real-time framework that incrementally builds a consistent 3D semantic scene graph of a scene given an RGB image sequence. Our method consists of a novel incremental entity estimation pipeline and a scene graph prediction network."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.02743","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/2305.02743/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":"2305.02743","created_at":"2026-07-05T06:07:39.801070+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.02743v2","created_at":"2026-07-05T06:07:39.801070+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.02743","created_at":"2026-07-05T06:07:39.801070+00:00"},{"alias_kind":"pith_short_12","alias_value":"3PM4N7EYECOL","created_at":"2026-07-05T06:07:39.801070+00:00"},{"alias_kind":"pith_short_16","alias_value":"3PM4N7EYECOLGRE5","created_at":"2026-07-05T06:07:39.801070+00:00"},{"alias_kind":"pith_short_8","alias_value":"3PM4N7EY","created_at":"2026-07-05T06:07:39.801070+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21788","citing_title":"SceneGraphGrounder: Zero-Shot 3D Visual Grounding via Structured Scene Graph Matching","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3PM4N7EYECOLGRE5X2FIPATUEH","json":"https://pith.science/pith/3PM4N7EYECOLGRE5X2FIPATUEH.json","graph_json":"https://pith.science/api/pith-number/3PM4N7EYECOLGRE5X2FIPATUEH/graph.json","events_json":"https://pith.science/api/pith-number/3PM4N7EYECOLGRE5X2FIPATUEH/events.json","paper":"https://pith.science/paper/3PM4N7EY"},"agent_actions":{"view_html":"https://pith.science/pith/3PM4N7EYECOLGRE5X2FIPATUEH","download_json":"https://pith.science/pith/3PM4N7EYECOLGRE5X2FIPATUEH.json","view_paper":"https://pith.science/paper/3PM4N7EY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.02743&json=true","fetch_graph":"https://pith.science/api/pith-number/3PM4N7EYECOLGRE5X2FIPATUEH/graph.json","fetch_events":"https://pith.science/api/pith-number/3PM4N7EYECOLGRE5X2FIPATUEH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3PM4N7EYECOLGRE5X2FIPATUEH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3PM4N7EYECOLGRE5X2FIPATUEH/action/storage_attestation","attest_author":"https://pith.science/pith/3PM4N7EYECOLGRE5X2FIPATUEH/action/author_attestation","sign_citation":"https://pith.science/pith/3PM4N7EYECOLGRE5X2FIPATUEH/action/citation_signature","submit_replication":"https://pith.science/pith/3PM4N7EYECOLGRE5X2FIPATUEH/action/replication_record"}},"created_at":"2026-07-05T06:07:39.801070+00:00","updated_at":"2026-07-05T06:07:39.801070+00:00"}