{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SB3IPFMGTETDEXMA7NZMNBSOWF","short_pith_number":"pith:SB3IPFMG","schema_version":"1.0","canonical_sha256":"90768795869926325d80fb72c6864eb17819fcf7d52001ddf537b784f092f799","source":{"kind":"arxiv","id":"2112.03288","version":2},"attestation_state":"computed","paper":{"title":"Dense Depth Priors for Neural Radiance Fields from Sparse Input Views","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Barbara Roessle, Ben Mildenhall, Jonathan T. Barron, Matthias Nie{\\ss}ner, Pratul P. Srinivasan","submitted_at":"2021-12-06T19:00:02Z","abstract_excerpt":"Neural radiance fields (NeRF) encode a scene into a neural representation that enables photo-realistic rendering of novel views. However, a successful reconstruction from RGB images requires a large number of input views taken under static conditions - typically up to a few hundred images for room-size scenes. Our method aims to synthesize novel views of whole rooms from an order of magnitude fewer images. To this end, we leverage dense depth priors in order to constrain the NeRF optimization. First, we take advantage of the sparse depth data that is freely available from the structure from mo"},"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":"2112.03288","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-06T19:00:02Z","cross_cats_sorted":[],"title_canon_sha256":"d4089d7e39bec298b2ce4e441a150aa0a3b1ae261eb774eb359cd3374dc435cb","abstract_canon_sha256":"8891fdb88a25d3f2abb1569020ecc1a7ccd1bd0f28089fc8f50bde91d4fb5fd5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:17.142288Z","signature_b64":"n1H6Dh6oa9BezRpgLy+4dC1bYUHgUN4ZgZ/Y9HnK+EVPtfA8Q5PyWiMv85XZJowE+qxCQCVg9gtbVSi+Jmv6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90768795869926325d80fb72c6864eb17819fcf7d52001ddf537b784f092f799","last_reissued_at":"2026-07-05T04:12:17.141831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:17.141831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dense Depth Priors for Neural Radiance Fields from Sparse Input Views","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Barbara Roessle, Ben Mildenhall, Jonathan T. Barron, Matthias Nie{\\ss}ner, Pratul P. Srinivasan","submitted_at":"2021-12-06T19:00:02Z","abstract_excerpt":"Neural radiance fields (NeRF) encode a scene into a neural representation that enables photo-realistic rendering of novel views. However, a successful reconstruction from RGB images requires a large number of input views taken under static conditions - typically up to a few hundred images for room-size scenes. Our method aims to synthesize novel views of whole rooms from an order of magnitude fewer images. To this end, we leverage dense depth priors in order to constrain the NeRF optimization. First, we take advantage of the sparse depth data that is freely available from the structure from mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03288","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/2112.03288/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":"2112.03288","created_at":"2026-07-05T04:12:17.141880+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.03288v2","created_at":"2026-07-05T04:12:17.141880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03288","created_at":"2026-07-05T04:12:17.141880+00:00"},{"alias_kind":"pith_short_12","alias_value":"SB3IPFMGTETD","created_at":"2026-07-05T04:12:17.141880+00:00"},{"alias_kind":"pith_short_16","alias_value":"SB3IPFMGTETDEXMA","created_at":"2026-07-05T04:12:17.141880+00:00"},{"alias_kind":"pith_short_8","alias_value":"SB3IPFMG","created_at":"2026-07-05T04:12:17.141880+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.11102","citing_title":"RDG-GS: Relative Depth Guidance with Gaussian Splatting for Real-time Sparse-View 3D Rendering","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SB3IPFMGTETDEXMA7NZMNBSOWF","json":"https://pith.science/pith/SB3IPFMGTETDEXMA7NZMNBSOWF.json","graph_json":"https://pith.science/api/pith-number/SB3IPFMGTETDEXMA7NZMNBSOWF/graph.json","events_json":"https://pith.science/api/pith-number/SB3IPFMGTETDEXMA7NZMNBSOWF/events.json","paper":"https://pith.science/paper/SB3IPFMG"},"agent_actions":{"view_html":"https://pith.science/pith/SB3IPFMGTETDEXMA7NZMNBSOWF","download_json":"https://pith.science/pith/SB3IPFMGTETDEXMA7NZMNBSOWF.json","view_paper":"https://pith.science/paper/SB3IPFMG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.03288&json=true","fetch_graph":"https://pith.science/api/pith-number/SB3IPFMGTETDEXMA7NZMNBSOWF/graph.json","fetch_events":"https://pith.science/api/pith-number/SB3IPFMGTETDEXMA7NZMNBSOWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SB3IPFMGTETDEXMA7NZMNBSOWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SB3IPFMGTETDEXMA7NZMNBSOWF/action/storage_attestation","attest_author":"https://pith.science/pith/SB3IPFMGTETDEXMA7NZMNBSOWF/action/author_attestation","sign_citation":"https://pith.science/pith/SB3IPFMGTETDEXMA7NZMNBSOWF/action/citation_signature","submit_replication":"https://pith.science/pith/SB3IPFMGTETDEXMA7NZMNBSOWF/action/replication_record"}},"created_at":"2026-07-05T04:12:17.141880+00:00","updated_at":"2026-07-05T04:12:17.141880+00:00"}