{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FEXHSEZB4EZ4IUO547BXADSHJF","short_pith_number":"pith:FEXHSEZB","schema_version":"1.0","canonical_sha256":"292e791321e133c451dde7c3700e47495154b5db44900af24d5ac2428a2b845c","source":{"kind":"arxiv","id":"2402.13252","version":1},"attestation_state":"computed","paper":{"title":"Improving Robustness for Joint Optimization of Camera Poses and Decomposed Low-Rank Tensorial Radiance Fields","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo-Yu Cheng, Wei-Chen Chiu, Yu-Lun Liu","submitted_at":"2024-02-20T18:59:02Z","abstract_excerpt":"In this paper, we propose an algorithm that allows joint refinement of camera pose and scene geometry represented by decomposed low-rank tensor, using only 2D images as supervision. First, we conduct a pilot study based on a 1D signal and relate our findings to 3D scenarios, where the naive joint pose optimization on voxel-based NeRFs can easily lead to sub-optimal solutions. Moreover, based on the analysis of the frequency spectrum, we propose to apply convolutional Gaussian filters on 2D and 3D radiance fields for a coarse-to-fine training schedule that enables joint camera pose optimization"},"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":"2402.13252","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-20T18:59:02Z","cross_cats_sorted":[],"title_canon_sha256":"26dbca9833d8102569784030e70de3b0700c353ba193c1476aa460f5f27fa0d7","abstract_canon_sha256":"32549025e1cc667618eab293391352b259c58c97a6ba0266afe14af2271711a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:22.551089Z","signature_b64":"y/S8ShgZE6LUwBZmyyWPn/aavTIaPVme6v026PxYaIiXsOha+5W2jAN5gtg/aYaEsox8cW44K1sbu+79m8qCDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"292e791321e133c451dde7c3700e47495154b5db44900af24d5ac2428a2b845c","last_reissued_at":"2026-07-05T07:47:22.550601Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:22.550601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Robustness for Joint Optimization of Camera Poses and Decomposed Low-Rank Tensorial Radiance Fields","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo-Yu Cheng, Wei-Chen Chiu, Yu-Lun Liu","submitted_at":"2024-02-20T18:59:02Z","abstract_excerpt":"In this paper, we propose an algorithm that allows joint refinement of camera pose and scene geometry represented by decomposed low-rank tensor, using only 2D images as supervision. First, we conduct a pilot study based on a 1D signal and relate our findings to 3D scenarios, where the naive joint pose optimization on voxel-based NeRFs can easily lead to sub-optimal solutions. Moreover, based on the analysis of the frequency spectrum, we propose to apply convolutional Gaussian filters on 2D and 3D radiance fields for a coarse-to-fine training schedule that enables joint camera pose optimization"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13252","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/2402.13252/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":"2402.13252","created_at":"2026-07-05T07:47:22.550663+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.13252v1","created_at":"2026-07-05T07:47:22.550663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13252","created_at":"2026-07-05T07:47:22.550663+00:00"},{"alias_kind":"pith_short_12","alias_value":"FEXHSEZB4EZ4","created_at":"2026-07-05T07:47:22.550663+00:00"},{"alias_kind":"pith_short_16","alias_value":"FEXHSEZB4EZ4IUO5","created_at":"2026-07-05T07:47:22.550663+00:00"},{"alias_kind":"pith_short_8","alias_value":"FEXHSEZB","created_at":"2026-07-05T07:47:22.550663+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.13620","citing_title":"Robust SG-NeRF: Robust Scene Graph Aided Neural Surface Reconstruction","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FEXHSEZB4EZ4IUO547BXADSHJF","json":"https://pith.science/pith/FEXHSEZB4EZ4IUO547BXADSHJF.json","graph_json":"https://pith.science/api/pith-number/FEXHSEZB4EZ4IUO547BXADSHJF/graph.json","events_json":"https://pith.science/api/pith-number/FEXHSEZB4EZ4IUO547BXADSHJF/events.json","paper":"https://pith.science/paper/FEXHSEZB"},"agent_actions":{"view_html":"https://pith.science/pith/FEXHSEZB4EZ4IUO547BXADSHJF","download_json":"https://pith.science/pith/FEXHSEZB4EZ4IUO547BXADSHJF.json","view_paper":"https://pith.science/paper/FEXHSEZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.13252&json=true","fetch_graph":"https://pith.science/api/pith-number/FEXHSEZB4EZ4IUO547BXADSHJF/graph.json","fetch_events":"https://pith.science/api/pith-number/FEXHSEZB4EZ4IUO547BXADSHJF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FEXHSEZB4EZ4IUO547BXADSHJF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FEXHSEZB4EZ4IUO547BXADSHJF/action/storage_attestation","attest_author":"https://pith.science/pith/FEXHSEZB4EZ4IUO547BXADSHJF/action/author_attestation","sign_citation":"https://pith.science/pith/FEXHSEZB4EZ4IUO547BXADSHJF/action/citation_signature","submit_replication":"https://pith.science/pith/FEXHSEZB4EZ4IUO547BXADSHJF/action/replication_record"}},"created_at":"2026-07-05T07:47:22.550663+00:00","updated_at":"2026-07-05T07:47:22.550663+00:00"}