{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3ACXLPVY5IIH4H66VWJTSGOXOU","short_pith_number":"pith:3ACXLPVY","schema_version":"1.0","canonical_sha256":"d80575beb8ea107e1fdead933919d7750556eee5bf3dd5bc536b5e5ff460bb46","source":{"kind":"arxiv","id":"2304.01480","version":2},"attestation_state":"computed","paper":{"title":"FineRecon: Depth-aware Feed-forward Network for Detailed 3D Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Colburn, Anurag Ranjan, Baptiste Angles, Fangchang Ma, Liang Yang, Noah Stier, Yajie Yan","submitted_at":"2023-04-04T02:50:29Z","abstract_excerpt":"Recent works on 3D reconstruction from posed images have demonstrated that direct inference of scene-level 3D geometry without test-time optimization is feasible using deep neural networks, showing remarkable promise and high efficiency. However, the reconstructed geometry, typically represented as a 3D truncated signed distance function (TSDF), is often coarse without fine geometric details. To address this problem, we propose three effective solutions for improving the fidelity of inference-based 3D reconstructions. We first present a resolution-agnostic TSDF supervision strategy to provide "},"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":"2304.01480","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-04T02:50:29Z","cross_cats_sorted":[],"title_canon_sha256":"b00faeb7932d667c4e620143e2290d870adebb7efa029592e91b7f504d36eeec","abstract_canon_sha256":"a221f8debe31c18c9134ae36e7608ac4b211decf2869114389e2c4377ad190ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:43.268020Z","signature_b64":"L1pFKhqvAbBw5Rn+7hD1nzh378h0FMWfzq73vrPw8HDjiDX0RaBJ+VDXYnCNr53c1gNPv0aIEhT70zwtV5reDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d80575beb8ea107e1fdead933919d7750556eee5bf3dd5bc536b5e5ff460bb46","last_reissued_at":"2026-07-05T06:42:43.267569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:43.267569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FineRecon: Depth-aware Feed-forward Network for Detailed 3D Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Colburn, Anurag Ranjan, Baptiste Angles, Fangchang Ma, Liang Yang, Noah Stier, Yajie Yan","submitted_at":"2023-04-04T02:50:29Z","abstract_excerpt":"Recent works on 3D reconstruction from posed images have demonstrated that direct inference of scene-level 3D geometry without test-time optimization is feasible using deep neural networks, showing remarkable promise and high efficiency. However, the reconstructed geometry, typically represented as a 3D truncated signed distance function (TSDF), is often coarse without fine geometric details. To address this problem, we propose three effective solutions for improving the fidelity of inference-based 3D reconstructions. We first present a resolution-agnostic TSDF supervision strategy to provide "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.01480","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/2304.01480/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":"2304.01480","created_at":"2026-07-05T06:42:43.267620+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.01480v2","created_at":"2026-07-05T06:42:43.267620+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.01480","created_at":"2026-07-05T06:42:43.267620+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ACXLPVY5IIH","created_at":"2026-07-05T06:42:43.267620+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ACXLPVY5IIH4H66","created_at":"2026-07-05T06:42:43.267620+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ACXLPVY","created_at":"2026-07-05T06:42:43.267620+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23888","citing_title":"GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ACXLPVY5IIH4H66VWJTSGOXOU","json":"https://pith.science/pith/3ACXLPVY5IIH4H66VWJTSGOXOU.json","graph_json":"https://pith.science/api/pith-number/3ACXLPVY5IIH4H66VWJTSGOXOU/graph.json","events_json":"https://pith.science/api/pith-number/3ACXLPVY5IIH4H66VWJTSGOXOU/events.json","paper":"https://pith.science/paper/3ACXLPVY"},"agent_actions":{"view_html":"https://pith.science/pith/3ACXLPVY5IIH4H66VWJTSGOXOU","download_json":"https://pith.science/pith/3ACXLPVY5IIH4H66VWJTSGOXOU.json","view_paper":"https://pith.science/paper/3ACXLPVY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.01480&json=true","fetch_graph":"https://pith.science/api/pith-number/3ACXLPVY5IIH4H66VWJTSGOXOU/graph.json","fetch_events":"https://pith.science/api/pith-number/3ACXLPVY5IIH4H66VWJTSGOXOU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ACXLPVY5IIH4H66VWJTSGOXOU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ACXLPVY5IIH4H66VWJTSGOXOU/action/storage_attestation","attest_author":"https://pith.science/pith/3ACXLPVY5IIH4H66VWJTSGOXOU/action/author_attestation","sign_citation":"https://pith.science/pith/3ACXLPVY5IIH4H66VWJTSGOXOU/action/citation_signature","submit_replication":"https://pith.science/pith/3ACXLPVY5IIH4H66VWJTSGOXOU/action/replication_record"}},"created_at":"2026-07-05T06:42:43.267620+00:00","updated_at":"2026-07-05T06:42:43.267620+00:00"}