{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VTPFBRJZJT6HHWX547J3O6YBYX","short_pith_number":"pith:VTPFBRJZ","schema_version":"1.0","canonical_sha256":"acde50c5394cfc73dafde7d3b77b01c5f686129e3d5b46bc594ddddd9baa1f53","source":{"kind":"arxiv","id":"2504.08410","version":2},"attestation_state":"computed","paper":{"title":"PMNI: Pose-free Multi-view Normal Integration for Reflective and Textureless Surface Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Heng Guo, Mingzhi Pei, Xiangyi Wang, Xu Cao, Zhanyu Ma","submitted_at":"2025-04-11T10:16:55Z","abstract_excerpt":"Reflective and textureless surfaces remain a challenge in multi-view 3D reconstruction. Both camera pose calibration and shape reconstruction often fail due to insufficient or unreliable cross-view visual features. To address these issues, we present PMNI (Pose-free Multi-view Normal Integration), a neural surface reconstruction method that incorporates rich geometric information by leveraging surface normal maps instead of RGB images. By enforcing geometric constraints from surface normals and multi-view shape consistency within a neural signed distance function (SDF) optimization framework, "},"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":"2504.08410","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-11T10:16:55Z","cross_cats_sorted":[],"title_canon_sha256":"e00ca5920200b3a3b710d011fa9e1bdc2a42492ea14e567b2c75d75c92db12b6","abstract_canon_sha256":"ce0f61cc0a864cefddefc0d5afa55c8a02ed533e73059f47e324c841b8a5ece5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:31.380390Z","signature_b64":"U9eI8bs3oiQd7ZaVnxfBN5Fb2De0OVD5FyJ4yKNAj89F9Tf0fbuQATzkYQAIoSEv57Oovf42Kq/F8eYdBaSFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acde50c5394cfc73dafde7d3b77b01c5f686129e3d5b46bc594ddddd9baa1f53","last_reissued_at":"2026-07-05T10:48:31.379915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:31.379915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PMNI: Pose-free Multi-view Normal Integration for Reflective and Textureless Surface Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Heng Guo, Mingzhi Pei, Xiangyi Wang, Xu Cao, Zhanyu Ma","submitted_at":"2025-04-11T10:16:55Z","abstract_excerpt":"Reflective and textureless surfaces remain a challenge in multi-view 3D reconstruction. Both camera pose calibration and shape reconstruction often fail due to insufficient or unreliable cross-view visual features. To address these issues, we present PMNI (Pose-free Multi-view Normal Integration), a neural surface reconstruction method that incorporates rich geometric information by leveraging surface normal maps instead of RGB images. By enforcing geometric constraints from surface normals and multi-view shape consistency within a neural signed distance function (SDF) optimization framework, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08410","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/2504.08410/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":"2504.08410","created_at":"2026-07-05T10:48:31.379971+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.08410v2","created_at":"2026-07-05T10:48:31.379971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08410","created_at":"2026-07-05T10:48:31.379971+00:00"},{"alias_kind":"pith_short_12","alias_value":"VTPFBRJZJT6H","created_at":"2026-07-05T10:48:31.379971+00:00"},{"alias_kind":"pith_short_16","alias_value":"VTPFBRJZJT6HHWX5","created_at":"2026-07-05T10:48:31.379971+00:00"},{"alias_kind":"pith_short_8","alias_value":"VTPFBRJZ","created_at":"2026-07-05T10:48:31.379971+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.09604","citing_title":"A Hybrid Neural-Microfacet BRDF Model for Real-Time Rendering","ref_index":91,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VTPFBRJZJT6HHWX547J3O6YBYX","json":"https://pith.science/pith/VTPFBRJZJT6HHWX547J3O6YBYX.json","graph_json":"https://pith.science/api/pith-number/VTPFBRJZJT6HHWX547J3O6YBYX/graph.json","events_json":"https://pith.science/api/pith-number/VTPFBRJZJT6HHWX547J3O6YBYX/events.json","paper":"https://pith.science/paper/VTPFBRJZ"},"agent_actions":{"view_html":"https://pith.science/pith/VTPFBRJZJT6HHWX547J3O6YBYX","download_json":"https://pith.science/pith/VTPFBRJZJT6HHWX547J3O6YBYX.json","view_paper":"https://pith.science/paper/VTPFBRJZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.08410&json=true","fetch_graph":"https://pith.science/api/pith-number/VTPFBRJZJT6HHWX547J3O6YBYX/graph.json","fetch_events":"https://pith.science/api/pith-number/VTPFBRJZJT6HHWX547J3O6YBYX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VTPFBRJZJT6HHWX547J3O6YBYX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VTPFBRJZJT6HHWX547J3O6YBYX/action/storage_attestation","attest_author":"https://pith.science/pith/VTPFBRJZJT6HHWX547J3O6YBYX/action/author_attestation","sign_citation":"https://pith.science/pith/VTPFBRJZJT6HHWX547J3O6YBYX/action/citation_signature","submit_replication":"https://pith.science/pith/VTPFBRJZJT6HHWX547J3O6YBYX/action/replication_record"}},"created_at":"2026-07-05T10:48:31.379971+00:00","updated_at":"2026-07-05T10:48:31.379971+00:00"}