{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EI3SJA4QVLBDFQTKFOH2FMJEXN","short_pith_number":"pith:EI3SJA4Q","schema_version":"1.0","canonical_sha256":"2237248390aac232c26a2b8fa2b124bb5d171729ba86180544fb9d6a5ee20cb4","source":{"kind":"arxiv","id":"2512.18954","version":6},"attestation_state":"computed","paper":{"title":"VOIC: Visible-Occluded Integrated Guidance for 3D Semantic Scene Completion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A dual-decoder network separates visible and occluded region supervision to improve monocular 3D semantic scene completion.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiang Liu, Risa Higashita, Zaidao Han","submitted_at":"2025-12-22T02:05:45Z","abstract_excerpt":"Camera-based 3D Semantic Scene Completion (SSC) is a critical task for autonomous driving and robotic scene understanding. It aims to infer a complete 3D volumetric representation of both semantics and geometry from a single image. Existing methods typically focus on end-to-end 2D-to-3D feature lifting and voxel completion. However, they often overlook the interference between high-confidence visible-region perception and low-confidence occluded-region reasoning caused by single-image input, which can lead to feature dilution and error propagation.\n  To address these challenges, we introduce 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":true},"canonical_record":{"source":{"id":"2512.18954","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-22T02:05:45Z","cross_cats_sorted":[],"title_canon_sha256":"fa3c62e3185c209586a2e33983e1952dd1444423abc9b513d9fced709162884c","abstract_canon_sha256":"b6d6ee9ca2d4af5f716f8744fd28e6bfc98ad0d998db1db2a3f8f9404dcbeda4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:47.017508Z","signature_b64":"nHt+g0p8PsLzm9CbcAwLrv43oJSQO/8AFfuxw68IALmzyohdz7LjuvRXECExe6j1IDMI0XBdEjg50x0zwsYWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2237248390aac232c26a2b8fa2b124bb5d171729ba86180544fb9d6a5ee20cb4","last_reissued_at":"2026-06-03T01:05:47.017104Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:47.017104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VOIC: Visible-Occluded Integrated Guidance for 3D Semantic Scene Completion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A dual-decoder network separates visible and occluded region supervision to improve monocular 3D semantic scene completion.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiang Liu, Risa Higashita, Zaidao Han","submitted_at":"2025-12-22T02:05:45Z","abstract_excerpt":"Camera-based 3D Semantic Scene Completion (SSC) is a critical task for autonomous driving and robotic scene understanding. It aims to infer a complete 3D volumetric representation of both semantics and geometry from a single image. Existing methods typically focus on end-to-end 2D-to-3D feature lifting and voxel completion. However, they often overlook the interference between high-confidence visible-region perception and low-confidence occluded-region reasoning caused by single-image input, which can lead to feature dilution and error propagation.\n  To address these challenges, we introduce a"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"VOIC outperforms existing monocular SSC methods in both geometric completion and semantic segmentation accuracy, achieving state-of-the-art performance on the SemanticKITTI and SSCBench-KITTI360 benchmarks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that offline extraction of visible-region voxel labels from dense 3D ground truth cleanly separates supervision without introducing selection bias or losing critical information needed for coherent global reasoning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"VOIC decouples monocular 3D scene completion into visible semantic perception and occluded reasoning via VRLE and a dual-decoder architecture, achieving state-of-the-art results on SemanticKITTI and SSCBench-KITTI360.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A dual-decoder network separates visible and occluded region supervision to improve monocular 3D semantic scene completion.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2b0d49e3e466cc87352bbc68b461122cd52c8fdb586564ea63fbf696282d15df"},"source":{"id":"2512.18954","kind":"arxiv","version":6},"verdict":{"id":"052b3ca3-e4bb-4a6e-b2e5-cbde302cd0e4","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T20:31:46.478229Z","strongest_claim":"VOIC outperforms existing monocular SSC methods in both geometric completion and semantic segmentation accuracy, achieving state-of-the-art performance on the SemanticKITTI and SSCBench-KITTI360 benchmarks.","one_line_summary":"VOIC decouples monocular 3D scene completion into visible semantic perception and occluded reasoning via VRLE and a dual-decoder architecture, achieving state-of-the-art results on SemanticKITTI and SSCBench-KITTI360.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that offline extraction of visible-region voxel labels from dense 3D ground truth cleanly separates supervision without introducing selection bias or losing critical information needed for coherent global reasoning.","pith_extraction_headline":"A dual-decoder network separates visible and occluded region supervision to improve monocular 3D semantic scene completion."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2512.18954/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":2,"snapshot_sha256":"c63d8ddd510ff37ddbb65b0756445b495a2e30e8a8e76d42bd71d09cf2ed0392"},"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":"2512.18954","created_at":"2026-06-03T01:05:47.017178+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.18954v6","created_at":"2026-06-03T01:05:47.017178+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.18954","created_at":"2026-06-03T01:05:47.017178+00:00"},{"alias_kind":"pith_short_12","alias_value":"EI3SJA4QVLBD","created_at":"2026-06-03T01:05:47.017178+00:00"},{"alias_kind":"pith_short_16","alias_value":"EI3SJA4QVLBDFQTK","created_at":"2026-06-03T01:05:47.017178+00:00"},{"alias_kind":"pith_short_8","alias_value":"EI3SJA4Q","created_at":"2026-06-03T01:05:47.017178+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EI3SJA4QVLBDFQTKFOH2FMJEXN","json":"https://pith.science/pith/EI3SJA4QVLBDFQTKFOH2FMJEXN.json","graph_json":"https://pith.science/api/pith-number/EI3SJA4QVLBDFQTKFOH2FMJEXN/graph.json","events_json":"https://pith.science/api/pith-number/EI3SJA4QVLBDFQTKFOH2FMJEXN/events.json","paper":"https://pith.science/paper/EI3SJA4Q"},"agent_actions":{"view_html":"https://pith.science/pith/EI3SJA4QVLBDFQTKFOH2FMJEXN","download_json":"https://pith.science/pith/EI3SJA4QVLBDFQTKFOH2FMJEXN.json","view_paper":"https://pith.science/paper/EI3SJA4Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.18954&json=true","fetch_graph":"https://pith.science/api/pith-number/EI3SJA4QVLBDFQTKFOH2FMJEXN/graph.json","fetch_events":"https://pith.science/api/pith-number/EI3SJA4QVLBDFQTKFOH2FMJEXN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EI3SJA4QVLBDFQTKFOH2FMJEXN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EI3SJA4QVLBDFQTKFOH2FMJEXN/action/storage_attestation","attest_author":"https://pith.science/pith/EI3SJA4QVLBDFQTKFOH2FMJEXN/action/author_attestation","sign_citation":"https://pith.science/pith/EI3SJA4QVLBDFQTKFOH2FMJEXN/action/citation_signature","submit_replication":"https://pith.science/pith/EI3SJA4QVLBDFQTKFOH2FMJEXN/action/replication_record"}},"created_at":"2026-06-03T01:05:47.017178+00:00","updated_at":"2026-06-03T01:05:47.017178+00:00"}