{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:635DDMWH5IOJNT73RPKNJOVCEF","short_pith_number":"pith:635DDMWH","schema_version":"1.0","canonical_sha256":"f6fa31b2c7ea1c96cffb8bd4d4baa2216b30f811eceaf632a1be0240cec21637","source":{"kind":"arxiv","id":"2504.01647","version":2},"attestation_state":"computed","paper":{"title":"FlowR: Flowing from Sparse to Dense 3D Reconstructions","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jonathon Luiten, Katja Schwarz, Lorenzo Porzi, Marc Pollefeys, Nikhil Keetha, Norman M\\\"uller, Peter Kontschieder, Samuel Rota Bul\\`o, Tobias Fischer, Yung-Hsu Yang","submitted_at":"2025-04-02T11:57:01Z","abstract_excerpt":"3D Gaussian splatting enables high-quality novel view synthesis (NVS) at real-time frame rates. However, its quality drops sharply as we depart from the training views. Thus, dense captures are needed to match the high-quality expectations of applications like Virtual Reality (VR). However, such dense captures are very laborious and expensive to obtain. Existing works have explored using 2D generative models to alleviate this requirement by distillation or generating additional training views. These models typically rely on a noise-to-data generative process conditioned only on a handful of re"},"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":"2504.01647","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T11:57:01Z","cross_cats_sorted":[],"title_canon_sha256":"f989b109cc4e083ed4673a01f0a93d16ea346e6a14eec27d4d9964de6b72a67e","abstract_canon_sha256":"c7ec8c09cafb60298c642c0dfe41475ce4cd5d370aaed72a6f13878754fd3c2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:24.967096Z","signature_b64":"chIS6IPrzrYRtDET4wE8/t+LFKGohJjIUJmJiY/aaGRYYf4u+MZY2m3UrnRwG9QSV6N0hnrrRszjxke7Gy/5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6fa31b2c7ea1c96cffb8bd4d4baa2216b30f811eceaf632a1be0240cec21637","last_reissued_at":"2026-07-05T11:48:24.966599Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:24.966599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlowR: Flowing from Sparse to Dense 3D Reconstructions","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jonathon Luiten, Katja Schwarz, Lorenzo Porzi, Marc Pollefeys, Nikhil Keetha, Norman M\\\"uller, Peter Kontschieder, Samuel Rota Bul\\`o, Tobias Fischer, Yung-Hsu Yang","submitted_at":"2025-04-02T11:57:01Z","abstract_excerpt":"3D Gaussian splatting enables high-quality novel view synthesis (NVS) at real-time frame rates. However, its quality drops sharply as we depart from the training views. Thus, dense captures are needed to match the high-quality expectations of applications like Virtual Reality (VR). However, such dense captures are very laborious and expensive to obtain. Existing works have explored using 2D generative models to alleviate this requirement by distillation or generating additional training views. These models typically rely on a noise-to-data generative process conditioned only on a handful of re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01647","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/2504.01647/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":"2504.01647","created_at":"2026-07-05T11:48:24.966661+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.01647v2","created_at":"2026-07-05T11:48:24.966661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01647","created_at":"2026-07-05T11:48:24.966661+00:00"},{"alias_kind":"pith_short_12","alias_value":"635DDMWH5IOJ","created_at":"2026-07-05T11:48:24.966661+00:00"},{"alias_kind":"pith_short_16","alias_value":"635DDMWH5IOJNT73","created_at":"2026-07-05T11:48:24.966661+00:00"},{"alias_kind":"pith_short_8","alias_value":"635DDMWH","created_at":"2026-07-05T11:48:24.966661+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22481","citing_title":"Lighting-Consistent Object Transfer Across Radiance Fields","ref_index":232,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/635DDMWH5IOJNT73RPKNJOVCEF","json":"https://pith.science/pith/635DDMWH5IOJNT73RPKNJOVCEF.json","graph_json":"https://pith.science/api/pith-number/635DDMWH5IOJNT73RPKNJOVCEF/graph.json","events_json":"https://pith.science/api/pith-number/635DDMWH5IOJNT73RPKNJOVCEF/events.json","paper":"https://pith.science/paper/635DDMWH"},"agent_actions":{"view_html":"https://pith.science/pith/635DDMWH5IOJNT73RPKNJOVCEF","download_json":"https://pith.science/pith/635DDMWH5IOJNT73RPKNJOVCEF.json","view_paper":"https://pith.science/paper/635DDMWH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.01647&json=true","fetch_graph":"https://pith.science/api/pith-number/635DDMWH5IOJNT73RPKNJOVCEF/graph.json","fetch_events":"https://pith.science/api/pith-number/635DDMWH5IOJNT73RPKNJOVCEF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/635DDMWH5IOJNT73RPKNJOVCEF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/635DDMWH5IOJNT73RPKNJOVCEF/action/storage_attestation","attest_author":"https://pith.science/pith/635DDMWH5IOJNT73RPKNJOVCEF/action/author_attestation","sign_citation":"https://pith.science/pith/635DDMWH5IOJNT73RPKNJOVCEF/action/citation_signature","submit_replication":"https://pith.science/pith/635DDMWH5IOJNT73RPKNJOVCEF/action/replication_record"}},"created_at":"2026-07-05T11:48:24.966661+00:00","updated_at":"2026-07-05T11:48:24.966661+00:00"}