{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2ANRQDQRNNSRGDOCIGGGA37SCR","short_pith_number":"pith:2ANRQDQR","schema_version":"1.0","canonical_sha256":"d01b180e116b65130dc2418c606ff2147ba6a997c0dfbb086d1160f30d6309cb","source":{"kind":"arxiv","id":"2104.06405","version":2},"attestation_state":"computed","paper":{"title":"BARF: Bundle-Adjusting Neural Radiance Fields","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Antonio Torralba, Chen-Hsuan Lin, Simon Lucey, Wei-Chiu Ma","submitted_at":"2021-04-13T17:59:51Z","abstract_excerpt":"Neural Radiance Fields (NeRF) have recently gained a surge of interest within the computer vision community for its power to synthesize photorealistic novel views of real-world scenes. One limitation of NeRF, however, is its requirement of accurate camera poses to learn the scene representations. In this paper, we propose Bundle-Adjusting Neural Radiance Fields (BARF) for training NeRF from imperfect (or even unknown) camera poses -- the joint problem of learning neural 3D representations and registering camera frames. We establish a theoretical connection to classical image alignment and show"},"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":"2104.06405","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-13T17:59:51Z","cross_cats_sorted":["cs.GR","cs.LG","cs.RO"],"title_canon_sha256":"20fcae728f6a50e5f2677d5c163851871ed1b0d3b6ad12ba8af7b954c8847771","abstract_canon_sha256":"6be5e1cb12bea1a52304dabf2fab2e57e02e8e63ac052dfa74bd6beeb194f9dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:07:06.114282Z","signature_b64":"OQX5E+8DkYZcBOrYlxo4ULppuTpREw9l79+QOPUx8n3myWG/V1AqiR265n/jDzB5ZjqIrUdlApPzY9GaS86MBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d01b180e116b65130dc2418c606ff2147ba6a997c0dfbb086d1160f30d6309cb","last_reissued_at":"2026-07-05T03:07:06.113930Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:07:06.113930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BARF: Bundle-Adjusting Neural Radiance Fields","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Antonio Torralba, Chen-Hsuan Lin, Simon Lucey, Wei-Chiu Ma","submitted_at":"2021-04-13T17:59:51Z","abstract_excerpt":"Neural Radiance Fields (NeRF) have recently gained a surge of interest within the computer vision community for its power to synthesize photorealistic novel views of real-world scenes. One limitation of NeRF, however, is its requirement of accurate camera poses to learn the scene representations. In this paper, we propose Bundle-Adjusting Neural Radiance Fields (BARF) for training NeRF from imperfect (or even unknown) camera poses -- the joint problem of learning neural 3D representations and registering camera frames. We establish a theoretical connection to classical image alignment and show"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06405","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/2104.06405/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":"2104.06405","created_at":"2026-07-05T03:07:06.113985+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.06405v2","created_at":"2026-07-05T03:07:06.113985+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06405","created_at":"2026-07-05T03:07:06.113985+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ANRQDQRNNSR","created_at":"2026-07-05T03:07:06.113985+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ANRQDQRNNSRGDOC","created_at":"2026-07-05T03:07:06.113985+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ANRQDQR","created_at":"2026-07-05T03:07:06.113985+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.01386","citing_title":"Construction of Digital Terrain Maps from Multi-view Satellite Imagery using Neural Volume Rendering","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2ANRQDQRNNSRGDOCIGGGA37SCR","json":"https://pith.science/pith/2ANRQDQRNNSRGDOCIGGGA37SCR.json","graph_json":"https://pith.science/api/pith-number/2ANRQDQRNNSRGDOCIGGGA37SCR/graph.json","events_json":"https://pith.science/api/pith-number/2ANRQDQRNNSRGDOCIGGGA37SCR/events.json","paper":"https://pith.science/paper/2ANRQDQR"},"agent_actions":{"view_html":"https://pith.science/pith/2ANRQDQRNNSRGDOCIGGGA37SCR","download_json":"https://pith.science/pith/2ANRQDQRNNSRGDOCIGGGA37SCR.json","view_paper":"https://pith.science/paper/2ANRQDQR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.06405&json=true","fetch_graph":"https://pith.science/api/pith-number/2ANRQDQRNNSRGDOCIGGGA37SCR/graph.json","fetch_events":"https://pith.science/api/pith-number/2ANRQDQRNNSRGDOCIGGGA37SCR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ANRQDQRNNSRGDOCIGGGA37SCR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ANRQDQRNNSRGDOCIGGGA37SCR/action/storage_attestation","attest_author":"https://pith.science/pith/2ANRQDQRNNSRGDOCIGGGA37SCR/action/author_attestation","sign_citation":"https://pith.science/pith/2ANRQDQRNNSRGDOCIGGGA37SCR/action/citation_signature","submit_replication":"https://pith.science/pith/2ANRQDQRNNSRGDOCIGGGA37SCR/action/replication_record"}},"created_at":"2026-07-05T03:07:06.113985+00:00","updated_at":"2026-07-05T03:07:06.113985+00:00"}