{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FL7F5OH44ITGLY4XIELHSPF7WW","short_pith_number":"pith:FL7F5OH4","schema_version":"1.0","canonical_sha256":"2afe5eb8fce22665e3974116793cbfb5a360d5ba69042443c5b9acffe97637da","source":{"kind":"arxiv","id":"2306.04699","version":4},"attestation_state":"computed","paper":{"title":"DiViNeT: 3D Reconstruction from Disparate Views via Neural Template Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aditya Vora, Akshay Gadi Patil, Hao Zhang","submitted_at":"2023-06-07T18:05:14Z","abstract_excerpt":"We present a volume rendering-based neural surface reconstruction method that takes as few as three disparate RGB images as input. Our key idea is to regularize the reconstruction, which is severely ill-posed and leaving significant gaps between the sparse views, by learning a set of neural templates to act as surface priors. Our method, coined DiViNet, operates in two stages. It first learns the templates, in the form of 3D Gaussian functions, across different scenes, without 3D supervision. In the reconstruction stage, our predicted templates serve as anchors to help \"stitch'' the surfaces o"},"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":"2306.04699","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-07T18:05:14Z","cross_cats_sorted":[],"title_canon_sha256":"2dbb209c13111cfa7c07f21daddf9a85f0ad435961d127dad3bdb72108e6b373","abstract_canon_sha256":"55f3fd8157dad675bc8d86974a8892aafaac28043740c405377f8a27599b7689"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:08.258553Z","signature_b64":"ms77PNVwZ5sD5Rc44Eye8itGSpMJSPaUpKnPTCD/ud2vEB8nj0G/XJkhbwiuumXnipq9nhQfaV9LHIFxXlrEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2afe5eb8fce22665e3974116793cbfb5a360d5ba69042443c5b9acffe97637da","last_reissued_at":"2026-07-05T07:08:08.258079Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:08.258079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiViNeT: 3D Reconstruction from Disparate Views via Neural Template Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aditya Vora, Akshay Gadi Patil, Hao Zhang","submitted_at":"2023-06-07T18:05:14Z","abstract_excerpt":"We present a volume rendering-based neural surface reconstruction method that takes as few as three disparate RGB images as input. Our key idea is to regularize the reconstruction, which is severely ill-posed and leaving significant gaps between the sparse views, by learning a set of neural templates to act as surface priors. Our method, coined DiViNet, operates in two stages. It first learns the templates, in the form of 3D Gaussian functions, across different scenes, without 3D supervision. In the reconstruction stage, our predicted templates serve as anchors to help \"stitch'' the surfaces o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04699","kind":"arxiv","version":4},"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/2306.04699/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":"2306.04699","created_at":"2026-07-05T07:08:08.258137+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.04699v4","created_at":"2026-07-05T07:08:08.258137+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04699","created_at":"2026-07-05T07:08:08.258137+00:00"},{"alias_kind":"pith_short_12","alias_value":"FL7F5OH44ITG","created_at":"2026-07-05T07:08:08.258137+00:00"},{"alias_kind":"pith_short_16","alias_value":"FL7F5OH44ITGLY4X","created_at":"2026-07-05T07:08:08.258137+00:00"},{"alias_kind":"pith_short_8","alias_value":"FL7F5OH4","created_at":"2026-07-05T07:08:08.258137+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16406","citing_title":"Sparse-View 3D Reconstruction: Recent Advances and Open Challenges","ref_index":65,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FL7F5OH44ITGLY4XIELHSPF7WW","json":"https://pith.science/pith/FL7F5OH44ITGLY4XIELHSPF7WW.json","graph_json":"https://pith.science/api/pith-number/FL7F5OH44ITGLY4XIELHSPF7WW/graph.json","events_json":"https://pith.science/api/pith-number/FL7F5OH44ITGLY4XIELHSPF7WW/events.json","paper":"https://pith.science/paper/FL7F5OH4"},"agent_actions":{"view_html":"https://pith.science/pith/FL7F5OH44ITGLY4XIELHSPF7WW","download_json":"https://pith.science/pith/FL7F5OH44ITGLY4XIELHSPF7WW.json","view_paper":"https://pith.science/paper/FL7F5OH4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.04699&json=true","fetch_graph":"https://pith.science/api/pith-number/FL7F5OH44ITGLY4XIELHSPF7WW/graph.json","fetch_events":"https://pith.science/api/pith-number/FL7F5OH44ITGLY4XIELHSPF7WW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FL7F5OH44ITGLY4XIELHSPF7WW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FL7F5OH44ITGLY4XIELHSPF7WW/action/storage_attestation","attest_author":"https://pith.science/pith/FL7F5OH44ITGLY4XIELHSPF7WW/action/author_attestation","sign_citation":"https://pith.science/pith/FL7F5OH44ITGLY4XIELHSPF7WW/action/citation_signature","submit_replication":"https://pith.science/pith/FL7F5OH44ITGLY4XIELHSPF7WW/action/replication_record"}},"created_at":"2026-07-05T07:08:08.258137+00:00","updated_at":"2026-07-05T07:08:08.258137+00:00"}