{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DTVFJRQJGSIW6YWWQ3MNGDESQN","short_pith_number":"pith:DTVFJRQJ","schema_version":"1.0","canonical_sha256":"1cea54c60934916f62d686d8d30c9283746739fcb30bb28b91fceaa966b40fb5","source":{"kind":"arxiv","id":"2304.14633","version":3},"attestation_state":"computed","paper":{"title":"CVRecon: Rethinking 3D Geometric Feature Learning For Neural Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Bing Li, Liang Yang, Pengsheng Guo, Ziyue Feng","submitted_at":"2023-04-28T05:30:19Z","abstract_excerpt":"Recent advances in neural reconstruction using posed image sequences have made remarkable progress. However, due to the lack of depth information, existing volumetric-based techniques simply duplicate 2D image features of the object surface along the entire camera ray. We contend this duplication introduces noise in empty and occluded spaces, posing challenges for producing high-quality 3D geometry. Drawing inspiration from traditional multi-view stereo methods, we propose an end-to-end 3D neural reconstruction framework CVRecon, designed to exploit the rich geometric embedding in the cost vol"},"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":"2304.14633","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-28T05:30:19Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"16abd845174470fa1c385700541cc0fb92446ce4b69830a5ec899046fbacd51c","abstract_canon_sha256":"49f25ad5c4efeb35ddd8dc0bd85088157675cf50be8d7ac969b810d9a935499b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:54.995212Z","signature_b64":"hLtde14WjBCFL62OVpRH1f4b6izz29k5SPauRd4dAGc/VBJHwomv0lE6rEuHdBjrtGXW5s7z7HWv/d8Y0z7GDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cea54c60934916f62d686d8d30c9283746739fcb30bb28b91fceaa966b40fb5","last_reissued_at":"2026-07-05T06:50:54.994677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:54.994677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CVRecon: Rethinking 3D Geometric Feature Learning For Neural Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Bing Li, Liang Yang, Pengsheng Guo, Ziyue Feng","submitted_at":"2023-04-28T05:30:19Z","abstract_excerpt":"Recent advances in neural reconstruction using posed image sequences have made remarkable progress. However, due to the lack of depth information, existing volumetric-based techniques simply duplicate 2D image features of the object surface along the entire camera ray. We contend this duplication introduces noise in empty and occluded spaces, posing challenges for producing high-quality 3D geometry. Drawing inspiration from traditional multi-view stereo methods, we propose an end-to-end 3D neural reconstruction framework CVRecon, designed to exploit the rich geometric embedding in the cost vol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14633","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/2304.14633/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":"2304.14633","created_at":"2026-07-05T06:50:54.994752+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.14633v3","created_at":"2026-07-05T06:50:54.994752+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14633","created_at":"2026-07-05T06:50:54.994752+00:00"},{"alias_kind":"pith_short_12","alias_value":"DTVFJRQJGSIW","created_at":"2026-07-05T06:50:54.994752+00:00"},{"alias_kind":"pith_short_16","alias_value":"DTVFJRQJGSIW6YWW","created_at":"2026-07-05T06:50:54.994752+00:00"},{"alias_kind":"pith_short_8","alias_value":"DTVFJRQJ","created_at":"2026-07-05T06:50:54.994752+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DTVFJRQJGSIW6YWWQ3MNGDESQN","json":"https://pith.science/pith/DTVFJRQJGSIW6YWWQ3MNGDESQN.json","graph_json":"https://pith.science/api/pith-number/DTVFJRQJGSIW6YWWQ3MNGDESQN/graph.json","events_json":"https://pith.science/api/pith-number/DTVFJRQJGSIW6YWWQ3MNGDESQN/events.json","paper":"https://pith.science/paper/DTVFJRQJ"},"agent_actions":{"view_html":"https://pith.science/pith/DTVFJRQJGSIW6YWWQ3MNGDESQN","download_json":"https://pith.science/pith/DTVFJRQJGSIW6YWWQ3MNGDESQN.json","view_paper":"https://pith.science/paper/DTVFJRQJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.14633&json=true","fetch_graph":"https://pith.science/api/pith-number/DTVFJRQJGSIW6YWWQ3MNGDESQN/graph.json","fetch_events":"https://pith.science/api/pith-number/DTVFJRQJGSIW6YWWQ3MNGDESQN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DTVFJRQJGSIW6YWWQ3MNGDESQN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DTVFJRQJGSIW6YWWQ3MNGDESQN/action/storage_attestation","attest_author":"https://pith.science/pith/DTVFJRQJGSIW6YWWQ3MNGDESQN/action/author_attestation","sign_citation":"https://pith.science/pith/DTVFJRQJGSIW6YWWQ3MNGDESQN/action/citation_signature","submit_replication":"https://pith.science/pith/DTVFJRQJGSIW6YWWQ3MNGDESQN/action/replication_record"}},"created_at":"2026-07-05T06:50:54.994752+00:00","updated_at":"2026-07-05T06:50:54.994752+00:00"}