{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YFIDE6K5QRHKPTSG72ZS4VKUGB","short_pith_number":"pith:YFIDE6K5","schema_version":"1.0","canonical_sha256":"c15032795d844ea7ce46feb32e5554307af5499aa92aa8d3da5a246f6977cb3b","source":{"kind":"arxiv","id":"2305.11031","version":1},"attestation_state":"computed","paper":{"title":"ConsistentNeRF: Enhancing Neural Radiance Fields with 3D Consistency for Sparse View Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gim Hee Lee, Kaichen Zhou, Kaiyu Li, Lanqing Hong, Longhui Yu, Shoukang Hu, Tianyang Hu, Zhenguo Li, Ziwei Liu","submitted_at":"2023-05-18T15:18:01Z","abstract_excerpt":"Neural Radiance Fields (NeRF) has demonstrated remarkable 3D reconstruction capabilities with dense view images. However, its performance significantly deteriorates under sparse view settings. We observe that learning the 3D consistency of pixels among different views is crucial for improving reconstruction quality in such cases. In this paper, we propose ConsistentNeRF, a method that leverages depth information to regularize both multi-view and single-view 3D consistency among pixels. Specifically, ConsistentNeRF employs depth-derived geometry information and a depth-invariant loss to concent"},"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":"2305.11031","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-18T15:18:01Z","cross_cats_sorted":[],"title_canon_sha256":"d2cc412e5fd8fd20e8a829df00343d1fb14498c1ba40561365d61637b2e28cff","abstract_canon_sha256":"2a81f13a16a23da9fba7f219e53a76369448b00ecc401f67cb7472e3f9fbd8c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:29.521515Z","signature_b64":"KqdCqlgqL9fr3EaaIn8WbKAHVX2TzE0fOfIWyXVs0YSD++cFMmL+sYa86DnjGibDPK2Cy+JS444wi5ZAjcQOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c15032795d844ea7ce46feb32e5554307af5499aa92aa8d3da5a246f6977cb3b","last_reissued_at":"2026-07-05T06:11:29.521035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:29.521035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ConsistentNeRF: Enhancing Neural Radiance Fields with 3D Consistency for Sparse View Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gim Hee Lee, Kaichen Zhou, Kaiyu Li, Lanqing Hong, Longhui Yu, Shoukang Hu, Tianyang Hu, Zhenguo Li, Ziwei Liu","submitted_at":"2023-05-18T15:18:01Z","abstract_excerpt":"Neural Radiance Fields (NeRF) has demonstrated remarkable 3D reconstruction capabilities with dense view images. However, its performance significantly deteriorates under sparse view settings. We observe that learning the 3D consistency of pixels among different views is crucial for improving reconstruction quality in such cases. In this paper, we propose ConsistentNeRF, a method that leverages depth information to regularize both multi-view and single-view 3D consistency among pixels. Specifically, ConsistentNeRF employs depth-derived geometry information and a depth-invariant loss to concent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11031","kind":"arxiv","version":1},"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/2305.11031/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":"2305.11031","created_at":"2026-07-05T06:11:29.521093+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11031v1","created_at":"2026-07-05T06:11:29.521093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11031","created_at":"2026-07-05T06:11:29.521093+00:00"},{"alias_kind":"pith_short_12","alias_value":"YFIDE6K5QRHK","created_at":"2026-07-05T06:11:29.521093+00:00"},{"alias_kind":"pith_short_16","alias_value":"YFIDE6K5QRHKPTSG","created_at":"2026-07-05T06:11:29.521093+00:00"},{"alias_kind":"pith_short_8","alias_value":"YFIDE6K5","created_at":"2026-07-05T06:11:29.521093+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":72,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YFIDE6K5QRHKPTSG72ZS4VKUGB","json":"https://pith.science/pith/YFIDE6K5QRHKPTSG72ZS4VKUGB.json","graph_json":"https://pith.science/api/pith-number/YFIDE6K5QRHKPTSG72ZS4VKUGB/graph.json","events_json":"https://pith.science/api/pith-number/YFIDE6K5QRHKPTSG72ZS4VKUGB/events.json","paper":"https://pith.science/paper/YFIDE6K5"},"agent_actions":{"view_html":"https://pith.science/pith/YFIDE6K5QRHKPTSG72ZS4VKUGB","download_json":"https://pith.science/pith/YFIDE6K5QRHKPTSG72ZS4VKUGB.json","view_paper":"https://pith.science/paper/YFIDE6K5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11031&json=true","fetch_graph":"https://pith.science/api/pith-number/YFIDE6K5QRHKPTSG72ZS4VKUGB/graph.json","fetch_events":"https://pith.science/api/pith-number/YFIDE6K5QRHKPTSG72ZS4VKUGB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YFIDE6K5QRHKPTSG72ZS4VKUGB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YFIDE6K5QRHKPTSG72ZS4VKUGB/action/storage_attestation","attest_author":"https://pith.science/pith/YFIDE6K5QRHKPTSG72ZS4VKUGB/action/author_attestation","sign_citation":"https://pith.science/pith/YFIDE6K5QRHKPTSG72ZS4VKUGB/action/citation_signature","submit_replication":"https://pith.science/pith/YFIDE6K5QRHKPTSG72ZS4VKUGB/action/replication_record"}},"created_at":"2026-07-05T06:11:29.521093+00:00","updated_at":"2026-07-05T06:11:29.521093+00:00"}