{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P4XGEUMXIHD4GYWRCBDMNU3AM7","short_pith_number":"pith:P4XGEUMX","schema_version":"1.0","canonical_sha256":"7f2e62519741c7c362d11046c6d36067e8e1a99e0e76bc516d857da9d2f26299","source":{"kind":"arxiv","id":"2503.12535","version":1},"attestation_state":"computed","paper":{"title":"SPC-GS: Gaussian Splatting with Semantic-Prompt Consistency for Indoor Open-World Free-view Synthesis from Sparse Inputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guibiao Liao, Guoping Qiu, Kanglin Liu, Qing Li, Zhenyu Bao","submitted_at":"2025-03-16T14:59:00Z","abstract_excerpt":"3D Gaussian Splatting-based indoor open-world free-view synthesis approaches have shown significant performance with dense input images. However, they exhibit poor performance when confronted with sparse inputs, primarily due to the sparse distribution of Gaussian points and insufficient view supervision. To relieve these challenges, we propose SPC-GS, leveraging Scene-layout-based Gaussian Initialization (SGI) and Semantic-Prompt Consistency (SPC) Regularization for open-world free view synthesis with sparse inputs. Specifically, SGI provides a dense, scene-layout-based Gaussian distribution "},"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":"2503.12535","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T14:59:00Z","cross_cats_sorted":[],"title_canon_sha256":"aa6a0c52d5791929977f2d82c06ade3c330d9fcf26a4a38b8aa2e42dcb9677ee","abstract_canon_sha256":"125325497808f5613cf8acc40f1e1f897c4eeb55770e2b535b48b0feb74ff5b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:15.675427Z","signature_b64":"fr1hjKW9lx68QvN/lJk5XkZ3LwXE8MuxdImJBxYFDp9Oaq/zYego1YExyZLyLwR94hBH46yqFTbXPzTDdBr2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f2e62519741c7c362d11046c6d36067e8e1a99e0e76bc516d857da9d2f26299","last_reissued_at":"2026-07-05T10:32:15.674437Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:15.674437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPC-GS: Gaussian Splatting with Semantic-Prompt Consistency for Indoor Open-World Free-view Synthesis from Sparse Inputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guibiao Liao, Guoping Qiu, Kanglin Liu, Qing Li, Zhenyu Bao","submitted_at":"2025-03-16T14:59:00Z","abstract_excerpt":"3D Gaussian Splatting-based indoor open-world free-view synthesis approaches have shown significant performance with dense input images. However, they exhibit poor performance when confronted with sparse inputs, primarily due to the sparse distribution of Gaussian points and insufficient view supervision. To relieve these challenges, we propose SPC-GS, leveraging Scene-layout-based Gaussian Initialization (SGI) and Semantic-Prompt Consistency (SPC) Regularization for open-world free view synthesis with sparse inputs. Specifically, SGI provides a dense, scene-layout-based Gaussian distribution "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12535","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/2503.12535/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":"2503.12535","created_at":"2026-07-05T10:32:15.674607+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.12535v1","created_at":"2026-07-05T10:32:15.674607+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12535","created_at":"2026-07-05T10:32:15.674607+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4XGEUMXIHD4","created_at":"2026-07-05T10:32:15.674607+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4XGEUMXIHD4GYWR","created_at":"2026-07-05T10:32:15.674607+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4XGEUMX","created_at":"2026-07-05T10:32:15.674607+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.05204","citing_title":"OGGSplat: Open Gaussian Growing for Generalizable Reconstruction with Expanded Field-of-View","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P4XGEUMXIHD4GYWRCBDMNU3AM7","json":"https://pith.science/pith/P4XGEUMXIHD4GYWRCBDMNU3AM7.json","graph_json":"https://pith.science/api/pith-number/P4XGEUMXIHD4GYWRCBDMNU3AM7/graph.json","events_json":"https://pith.science/api/pith-number/P4XGEUMXIHD4GYWRCBDMNU3AM7/events.json","paper":"https://pith.science/paper/P4XGEUMX"},"agent_actions":{"view_html":"https://pith.science/pith/P4XGEUMXIHD4GYWRCBDMNU3AM7","download_json":"https://pith.science/pith/P4XGEUMXIHD4GYWRCBDMNU3AM7.json","view_paper":"https://pith.science/paper/P4XGEUMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.12535&json=true","fetch_graph":"https://pith.science/api/pith-number/P4XGEUMXIHD4GYWRCBDMNU3AM7/graph.json","fetch_events":"https://pith.science/api/pith-number/P4XGEUMXIHD4GYWRCBDMNU3AM7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4XGEUMXIHD4GYWRCBDMNU3AM7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4XGEUMXIHD4GYWRCBDMNU3AM7/action/storage_attestation","attest_author":"https://pith.science/pith/P4XGEUMXIHD4GYWRCBDMNU3AM7/action/author_attestation","sign_citation":"https://pith.science/pith/P4XGEUMXIHD4GYWRCBDMNU3AM7/action/citation_signature","submit_replication":"https://pith.science/pith/P4XGEUMXIHD4GYWRCBDMNU3AM7/action/replication_record"}},"created_at":"2026-07-05T10:32:15.674607+00:00","updated_at":"2026-07-05T10:32:15.674607+00:00"}