{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DKKBX4HFRP4LTFD56FGOQFINPF","short_pith_number":"pith:DKKBX4HF","schema_version":"1.0","canonical_sha256":"1a941bf0e58bf8b9947df14ce8150d797fcf77cb683e8ed27b0fd14b5e76817e","source":{"kind":"arxiv","id":"2412.05908","version":2},"attestation_state":"computed","paper":{"title":"GBR: Generative Bundle Refinement for High-fidelity Gaussian Splatting with Enhanced Mesh Reconstruction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianing Zhang, Qionghai Dai, Xiaoyun Yuan, Yuchao Zheng, Ziwei Li","submitted_at":"2024-12-08T12:00:25Z","abstract_excerpt":"Gaussian splatting has gained attention for its efficient representation and rendering of 3D scenes using continuous Gaussian primitives. However, it struggles with sparse-view inputs due to limited geometric and photometric information, causing ambiguities in depth, shape, and texture.\n  we propose GBR: Generative Bundle Refinement, a method for high-fidelity Gaussian splatting and meshing using only 4-6 input views. GBR integrates a neural bundle adjustment module to enhance geometry accuracy and a generative depth refinement module to improve geometry fidelity. More specifically, the neural"},"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":"2412.05908","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-08T12:00:25Z","cross_cats_sorted":[],"title_canon_sha256":"c12471c1a27fc5782d8e60d3d6cc6edd63bd63f5e8e2c572cde78c718657f1e8","abstract_canon_sha256":"d23541ff8923cb1f601f16c2271ff278828a0512a7c97daf0bf53d4328df5311"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:09.681487Z","signature_b64":"rDSvmiaZYCmX/s5aCpPlguLfdnFY37kKWa7mLtlCIubVW4QqnZKbHmrxbvIfscTAHEzQQ3CsNVMe/BbgSJ2fDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a941bf0e58bf8b9947df14ce8150d797fcf77cb683e8ed27b0fd14b5e76817e","last_reissued_at":"2026-07-05T11:54:09.680973Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:09.680973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GBR: Generative Bundle Refinement for High-fidelity Gaussian Splatting with Enhanced Mesh Reconstruction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianing Zhang, Qionghai Dai, Xiaoyun Yuan, Yuchao Zheng, Ziwei Li","submitted_at":"2024-12-08T12:00:25Z","abstract_excerpt":"Gaussian splatting has gained attention for its efficient representation and rendering of 3D scenes using continuous Gaussian primitives. However, it struggles with sparse-view inputs due to limited geometric and photometric information, causing ambiguities in depth, shape, and texture.\n  we propose GBR: Generative Bundle Refinement, a method for high-fidelity Gaussian splatting and meshing using only 4-6 input views. GBR integrates a neural bundle adjustment module to enhance geometry accuracy and a generative depth refinement module to improve geometry fidelity. More specifically, the neural"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05908","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/2412.05908/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":"2412.05908","created_at":"2026-07-05T11:54:09.681033+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05908v2","created_at":"2026-07-05T11:54:09.681033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05908","created_at":"2026-07-05T11:54:09.681033+00:00"},{"alias_kind":"pith_short_12","alias_value":"DKKBX4HFRP4L","created_at":"2026-07-05T11:54:09.681033+00:00"},{"alias_kind":"pith_short_16","alias_value":"DKKBX4HFRP4LTFD5","created_at":"2026-07-05T11:54:09.681033+00:00"},{"alias_kind":"pith_short_8","alias_value":"DKKBX4HF","created_at":"2026-07-05T11:54:09.681033+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.05935","citing_title":"SurGSplat: Progressive Geometry-Constrained Gaussian Splatting for Surgical Scene Reconstruction","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DKKBX4HFRP4LTFD56FGOQFINPF","json":"https://pith.science/pith/DKKBX4HFRP4LTFD56FGOQFINPF.json","graph_json":"https://pith.science/api/pith-number/DKKBX4HFRP4LTFD56FGOQFINPF/graph.json","events_json":"https://pith.science/api/pith-number/DKKBX4HFRP4LTFD56FGOQFINPF/events.json","paper":"https://pith.science/paper/DKKBX4HF"},"agent_actions":{"view_html":"https://pith.science/pith/DKKBX4HFRP4LTFD56FGOQFINPF","download_json":"https://pith.science/pith/DKKBX4HFRP4LTFD56FGOQFINPF.json","view_paper":"https://pith.science/paper/DKKBX4HF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05908&json=true","fetch_graph":"https://pith.science/api/pith-number/DKKBX4HFRP4LTFD56FGOQFINPF/graph.json","fetch_events":"https://pith.science/api/pith-number/DKKBX4HFRP4LTFD56FGOQFINPF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DKKBX4HFRP4LTFD56FGOQFINPF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DKKBX4HFRP4LTFD56FGOQFINPF/action/storage_attestation","attest_author":"https://pith.science/pith/DKKBX4HFRP4LTFD56FGOQFINPF/action/author_attestation","sign_citation":"https://pith.science/pith/DKKBX4HFRP4LTFD56FGOQFINPF/action/citation_signature","submit_replication":"https://pith.science/pith/DKKBX4HFRP4LTFD56FGOQFINPF/action/replication_record"}},"created_at":"2026-07-05T11:54:09.681033+00:00","updated_at":"2026-07-05T11:54:09.681033+00:00"}