{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7TV443S44WBHUZKCW4P4YYCSFO","short_pith_number":"pith:7TV443S4","schema_version":"1.0","canonical_sha256":"fcebce6e5ce5827a6542b71fcc60522bbba05b2be91f2bd52f259bbaadeb9965","source":{"kind":"arxiv","id":"2405.12218","version":3},"attestation_state":"computed","paper":{"title":"MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangcong Wang, Liao Shen, Shoukang Hu, Tianqi Liu, Wei Li, Xinyi Ye, Yuhang Zang, Zhiguo Cao, Ziwei Liu","submitted_at":"2024-05-20T17:59:30Z","abstract_excerpt":"We present MVSGaussian, a new generalizable 3D Gaussian representation approach derived from Multi-View Stereo (MVS) that can efficiently reconstruct unseen scenes. Specifically, 1) we leverage MVS to encode geometry-aware Gaussian representations and decode them into Gaussian parameters. 2) To further enhance performance, we propose a hybrid Gaussian rendering that integrates an efficient volume rendering design for novel view synthesis. 3) To support fast fine-tuning for specific scenes, we introduce a multi-view geometric consistent aggregation strategy to effectively aggregate the point cl"},"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":"2405.12218","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-20T17:59:30Z","cross_cats_sorted":[],"title_canon_sha256":"721eca978103efa0d792248c4cf1d8503c75e273d75dc0024479dd9da921b1b8","abstract_canon_sha256":"1bf287164c85b11d03a22c6e0c0aa45f87c7a1fdcaf8a104aff4532f417072b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:55.965375Z","signature_b64":"hnFVh9oKnjOTgsRrRss0bUQ3J8lJIJiv5rGFlsVvXxlKyTylLOKR4IFUPacGSdcZKGOLRH1en0/Iv+DuKPWcCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcebce6e5ce5827a6542b71fcc60522bbba05b2be91f2bd52f259bbaadeb9965","last_reissued_at":"2026-07-05T08:43:55.964967Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:55.964967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangcong Wang, Liao Shen, Shoukang Hu, Tianqi Liu, Wei Li, Xinyi Ye, Yuhang Zang, Zhiguo Cao, Ziwei Liu","submitted_at":"2024-05-20T17:59:30Z","abstract_excerpt":"We present MVSGaussian, a new generalizable 3D Gaussian representation approach derived from Multi-View Stereo (MVS) that can efficiently reconstruct unseen scenes. Specifically, 1) we leverage MVS to encode geometry-aware Gaussian representations and decode them into Gaussian parameters. 2) To further enhance performance, we propose a hybrid Gaussian rendering that integrates an efficient volume rendering design for novel view synthesis. 3) To support fast fine-tuning for specific scenes, we introduce a multi-view geometric consistent aggregation strategy to effectively aggregate the point cl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12218","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/2405.12218/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":"2405.12218","created_at":"2026-07-05T08:43:55.965022+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.12218v3","created_at":"2026-07-05T08:43:55.965022+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12218","created_at":"2026-07-05T08:43:55.965022+00:00"},{"alias_kind":"pith_short_12","alias_value":"7TV443S44WBH","created_at":"2026-07-05T08:43:55.965022+00:00"},{"alias_kind":"pith_short_16","alias_value":"7TV443S44WBHUZKC","created_at":"2026-07-05T08:43:55.965022+00:00"},{"alias_kind":"pith_short_8","alias_value":"7TV443S4","created_at":"2026-07-05T08:43:55.965022+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.10267","citing_title":"Long-LRM++: Preserving Fine Details in Feed-Forward Wide-Coverage Reconstruction","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7TV443S44WBHUZKCW4P4YYCSFO","json":"https://pith.science/pith/7TV443S44WBHUZKCW4P4YYCSFO.json","graph_json":"https://pith.science/api/pith-number/7TV443S44WBHUZKCW4P4YYCSFO/graph.json","events_json":"https://pith.science/api/pith-number/7TV443S44WBHUZKCW4P4YYCSFO/events.json","paper":"https://pith.science/paper/7TV443S4"},"agent_actions":{"view_html":"https://pith.science/pith/7TV443S44WBHUZKCW4P4YYCSFO","download_json":"https://pith.science/pith/7TV443S44WBHUZKCW4P4YYCSFO.json","view_paper":"https://pith.science/paper/7TV443S4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.12218&json=true","fetch_graph":"https://pith.science/api/pith-number/7TV443S44WBHUZKCW4P4YYCSFO/graph.json","fetch_events":"https://pith.science/api/pith-number/7TV443S44WBHUZKCW4P4YYCSFO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7TV443S44WBHUZKCW4P4YYCSFO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7TV443S44WBHUZKCW4P4YYCSFO/action/storage_attestation","attest_author":"https://pith.science/pith/7TV443S44WBHUZKCW4P4YYCSFO/action/author_attestation","sign_citation":"https://pith.science/pith/7TV443S44WBHUZKCW4P4YYCSFO/action/citation_signature","submit_replication":"https://pith.science/pith/7TV443S44WBHUZKCW4P4YYCSFO/action/replication_record"}},"created_at":"2026-07-05T08:43:55.965022+00:00","updated_at":"2026-07-05T08:43:55.965022+00:00"}