{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2OQRF5IA5MYV6WTXHSVJ3GGCKL","short_pith_number":"pith:2OQRF5IA","schema_version":"1.0","canonical_sha256":"d3a112f500eb315f5a773caa9d98c252e5775b03a718b06dded13c134de06b32","source":{"kind":"arxiv","id":"2411.01749","version":1},"attestation_state":"computed","paper":{"title":"Multi-task Geometric Estimation of Depth and Surface Normal from Monocular 360{\\deg} Images","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangfang Zhang, Fang-Lue Zhang, Kun Huang, Neil A. Dodgson, Paul L. Rosin, Yu-Kun Lai","submitted_at":"2024-11-04T02:20:22Z","abstract_excerpt":"Geometric estimation is required for scene understanding and analysis in panoramic 360{\\deg} images. Current methods usually predict a single feature, such as depth or surface normal. These methods can lack robustness, especially when dealing with intricate textures or complex object surfaces. We introduce a novel multi-task learning (MTL) network that simultaneously estimates depth and surface normals from 360{\\deg} images. Our first innovation is our MTL architecture, which enhances predictions for both tasks by integrating geometric information from depth and surface normal estimation, enab"},"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":"2411.01749","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-04T02:20:22Z","cross_cats_sorted":[],"title_canon_sha256":"f2a738488d5b50054bd489603ab79262045c811f2cd3d0b511022f20b4de1097","abstract_canon_sha256":"12846f7ea2507365cc4afab837e0f31f8a3ae4d63a4d9b9c9a262f2859005cc7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:20.908518Z","signature_b64":"vrmg0pPqgrhWt5nHa+mQcxIzx5X2THrGwYVFl9jV/DdVhY8GToSA8v8zWr9CEas3UBGS27BlASJwaUcidAB6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3a112f500eb315f5a773caa9d98c252e5775b03a718b06dded13c134de06b32","last_reissued_at":"2026-07-05T11:11:20.908015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:20.908015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-task Geometric Estimation of Depth and Surface Normal from Monocular 360{\\deg} Images","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangfang Zhang, Fang-Lue Zhang, Kun Huang, Neil A. Dodgson, Paul L. Rosin, Yu-Kun Lai","submitted_at":"2024-11-04T02:20:22Z","abstract_excerpt":"Geometric estimation is required for scene understanding and analysis in panoramic 360{\\deg} images. Current methods usually predict a single feature, such as depth or surface normal. These methods can lack robustness, especially when dealing with intricate textures or complex object surfaces. We introduce a novel multi-task learning (MTL) network that simultaneously estimates depth and surface normals from 360{\\deg} images. Our first innovation is our MTL architecture, which enhances predictions for both tasks by integrating geometric information from depth and surface normal estimation, enab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01749","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/2411.01749/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":"2411.01749","created_at":"2026-07-05T11:11:20.908073+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.01749v1","created_at":"2026-07-05T11:11:20.908073+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01749","created_at":"2026-07-05T11:11:20.908073+00:00"},{"alias_kind":"pith_short_12","alias_value":"2OQRF5IA5MYV","created_at":"2026-07-05T11:11:20.908073+00:00"},{"alias_kind":"pith_short_16","alias_value":"2OQRF5IA5MYV6WTX","created_at":"2026-07-05T11:11:20.908073+00:00"},{"alias_kind":"pith_short_8","alias_value":"2OQRF5IA","created_at":"2026-07-05T11:11:20.908073+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26368","citing_title":"Unified Panoramic Geometry Estimation via Multi-View Foundation Models","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2OQRF5IA5MYV6WTXHSVJ3GGCKL","json":"https://pith.science/pith/2OQRF5IA5MYV6WTXHSVJ3GGCKL.json","graph_json":"https://pith.science/api/pith-number/2OQRF5IA5MYV6WTXHSVJ3GGCKL/graph.json","events_json":"https://pith.science/api/pith-number/2OQRF5IA5MYV6WTXHSVJ3GGCKL/events.json","paper":"https://pith.science/paper/2OQRF5IA"},"agent_actions":{"view_html":"https://pith.science/pith/2OQRF5IA5MYV6WTXHSVJ3GGCKL","download_json":"https://pith.science/pith/2OQRF5IA5MYV6WTXHSVJ3GGCKL.json","view_paper":"https://pith.science/paper/2OQRF5IA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.01749&json=true","fetch_graph":"https://pith.science/api/pith-number/2OQRF5IA5MYV6WTXHSVJ3GGCKL/graph.json","fetch_events":"https://pith.science/api/pith-number/2OQRF5IA5MYV6WTXHSVJ3GGCKL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2OQRF5IA5MYV6WTXHSVJ3GGCKL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2OQRF5IA5MYV6WTXHSVJ3GGCKL/action/storage_attestation","attest_author":"https://pith.science/pith/2OQRF5IA5MYV6WTXHSVJ3GGCKL/action/author_attestation","sign_citation":"https://pith.science/pith/2OQRF5IA5MYV6WTXHSVJ3GGCKL/action/citation_signature","submit_replication":"https://pith.science/pith/2OQRF5IA5MYV6WTXHSVJ3GGCKL/action/replication_record"}},"created_at":"2026-07-05T11:11:20.908073+00:00","updated_at":"2026-07-05T11:11:20.908073+00:00"}