{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JHHO2RLLRXUWTWOSO757YZKQ4W","short_pith_number":"pith:JHHO2RLL","schema_version":"1.0","canonical_sha256":"49ceed456b8de969d9d277fbfc6550e5a3a79acf8ef69894bfd205b72eefafb5","source":{"kind":"arxiv","id":"2503.16591","version":1},"attestation_state":"computed","paper":{"title":"UniK3D: Universal Camera Monocular 3D Estimation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christos Sakaridis, Luc Van Gool, Luigi Piccinelli, Mattia Segu, Siyuan Li, Wim Abbeloos, Yung-Hsu Yang","submitted_at":"2025-03-20T17:49:23Z","abstract_excerpt":"Monocular 3D estimation is crucial for visual perception. However, current methods fall short by relying on oversimplified assumptions, such as pinhole camera models or rectified images. These limitations severely restrict their general applicability, causing poor performance in real-world scenarios with fisheye or panoramic images and resulting in substantial context loss. To address this, we present UniK3D, the first generalizable method for monocular 3D estimation able to model any camera. Our method introduces a spherical 3D representation which allows for better disentanglement of camera "},"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":"2503.16591","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T17:49:23Z","cross_cats_sorted":[],"title_canon_sha256":"02354881043e93d66f334ba039077a45363f1f1de56797df44c84b7a7be2b19f","abstract_canon_sha256":"86235caeb529ad334e4193a349529e73fb3481fb3bba70cbb188e1e596aa56e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:44.864800Z","signature_b64":"ZfYyLPBXTSZA4Yg2UzKTjLqsO7g5TKLbrL6yNqsuNTTpZ9K40ZBRmUrhvofnFRat3W0KR8RJNm9aGPffUmVmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49ceed456b8de969d9d277fbfc6550e5a3a79acf8ef69894bfd205b72eefafb5","last_reissued_at":"2026-07-05T10:36:44.864261Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:44.864261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniK3D: Universal Camera Monocular 3D Estimation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christos Sakaridis, Luc Van Gool, Luigi Piccinelli, Mattia Segu, Siyuan Li, Wim Abbeloos, Yung-Hsu Yang","submitted_at":"2025-03-20T17:49:23Z","abstract_excerpt":"Monocular 3D estimation is crucial for visual perception. However, current methods fall short by relying on oversimplified assumptions, such as pinhole camera models or rectified images. These limitations severely restrict their general applicability, causing poor performance in real-world scenarios with fisheye or panoramic images and resulting in substantial context loss. To address this, we present UniK3D, the first generalizable method for monocular 3D estimation able to model any camera. Our method introduces a spherical 3D representation which allows for better disentanglement of camera "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16591","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/2503.16591/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":"2503.16591","created_at":"2026-07-05T10:36:44.864341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.16591v1","created_at":"2026-07-05T10:36:44.864341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16591","created_at":"2026-07-05T10:36:44.864341+00:00"},{"alias_kind":"pith_short_12","alias_value":"JHHO2RLLRXUW","created_at":"2026-07-05T10:36:44.864341+00:00"},{"alias_kind":"pith_short_16","alias_value":"JHHO2RLLRXUWTWOS","created_at":"2026-07-05T10:36:44.864341+00:00"},{"alias_kind":"pith_short_8","alias_value":"JHHO2RLL","created_at":"2026-07-05T10:36:44.864341+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.10934","citing_title":"ViPE: Video Pose Engine for 3D Geometric Perception","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JHHO2RLLRXUWTWOSO757YZKQ4W","json":"https://pith.science/pith/JHHO2RLLRXUWTWOSO757YZKQ4W.json","graph_json":"https://pith.science/api/pith-number/JHHO2RLLRXUWTWOSO757YZKQ4W/graph.json","events_json":"https://pith.science/api/pith-number/JHHO2RLLRXUWTWOSO757YZKQ4W/events.json","paper":"https://pith.science/paper/JHHO2RLL"},"agent_actions":{"view_html":"https://pith.science/pith/JHHO2RLLRXUWTWOSO757YZKQ4W","download_json":"https://pith.science/pith/JHHO2RLLRXUWTWOSO757YZKQ4W.json","view_paper":"https://pith.science/paper/JHHO2RLL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.16591&json=true","fetch_graph":"https://pith.science/api/pith-number/JHHO2RLLRXUWTWOSO757YZKQ4W/graph.json","fetch_events":"https://pith.science/api/pith-number/JHHO2RLLRXUWTWOSO757YZKQ4W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JHHO2RLLRXUWTWOSO757YZKQ4W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JHHO2RLLRXUWTWOSO757YZKQ4W/action/storage_attestation","attest_author":"https://pith.science/pith/JHHO2RLLRXUWTWOSO757YZKQ4W/action/author_attestation","sign_citation":"https://pith.science/pith/JHHO2RLLRXUWTWOSO757YZKQ4W/action/citation_signature","submit_replication":"https://pith.science/pith/JHHO2RLLRXUWTWOSO757YZKQ4W/action/replication_record"}},"created_at":"2026-07-05T10:36:44.864341+00:00","updated_at":"2026-07-05T10:36:44.864341+00:00"}