{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WDJHNYJGLEXKLW4UBL2KWFYSBG","short_pith_number":"pith:WDJHNYJG","schema_version":"1.0","canonical_sha256":"b0d276e126592ea5db940af4ab1712098bf36820df824f0486e01346625dd8fe","source":{"kind":"arxiv","id":"2605.26725","version":1},"attestation_state":"computed","paper":{"title":"Joint 2D-3D Segmentation and Association in Street-level Imaging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amir Melnikov, Masatoshi Okutomi, Masayuki Tanaka, Yusuke Monno","submitted_at":"2026-05-26T09:04:51Z","abstract_excerpt":"Accurate interpretation of street-level imagery is essential for large-scale urban mapping and the creation of Spatial Digital Twin (SDT) environments. This work presents a unified framework for joint 2D-3D segmentation and association that integrates visual semantics with multi-view geometric reasoning. Unlike conventional approaches that rely heavily on sequential frames for temporal tracking, our method leverages zero-shot detection and segmentation together with structure-from-motion reconstruction to establish stable cross-view correspondences. A 3D-driven association mechanism replaces t"},"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":"2605.26725","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T09:04:51Z","cross_cats_sorted":[],"title_canon_sha256":"6e88ffd0ae2972fdc0f909e7753d4ad969ea0b12045ec3a7afd4ae7df6010e34","abstract_canon_sha256":"fbbe43f2e8575ca4b3d80e5064be1bbfbd92a49cc25d68c7ab0f58a4e7a33232"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:09.397040Z","signature_b64":"AojOvo5SoUwkT4f+7rOtUAZdlwrCL6VorcpMSGJXDlRvLGeM2VSV5300XlswSnRrctoOJHZlW2ktnsUxX6WYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0d276e126592ea5db940af4ab1712098bf36820df824f0486e01346625dd8fe","last_reissued_at":"2026-05-27T01:06:09.396235Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:09.396235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint 2D-3D Segmentation and Association in Street-level Imaging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amir Melnikov, Masatoshi Okutomi, Masayuki Tanaka, Yusuke Monno","submitted_at":"2026-05-26T09:04:51Z","abstract_excerpt":"Accurate interpretation of street-level imagery is essential for large-scale urban mapping and the creation of Spatial Digital Twin (SDT) environments. This work presents a unified framework for joint 2D-3D segmentation and association that integrates visual semantics with multi-view geometric reasoning. Unlike conventional approaches that rely heavily on sequential frames for temporal tracking, our method leverages zero-shot detection and segmentation together with structure-from-motion reconstruction to establish stable cross-view correspondences. A 3D-driven association mechanism replaces t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26725","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/2605.26725/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":"2605.26725","created_at":"2026-05-27T01:06:09.396361+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26725v1","created_at":"2026-05-27T01:06:09.396361+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26725","created_at":"2026-05-27T01:06:09.396361+00:00"},{"alias_kind":"pith_short_12","alias_value":"WDJHNYJGLEXK","created_at":"2026-05-27T01:06:09.396361+00:00"},{"alias_kind":"pith_short_16","alias_value":"WDJHNYJGLEXKLW4U","created_at":"2026-05-27T01:06:09.396361+00:00"},{"alias_kind":"pith_short_8","alias_value":"WDJHNYJG","created_at":"2026-05-27T01:06:09.396361+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WDJHNYJGLEXKLW4UBL2KWFYSBG","json":"https://pith.science/pith/WDJHNYJGLEXKLW4UBL2KWFYSBG.json","graph_json":"https://pith.science/api/pith-number/WDJHNYJGLEXKLW4UBL2KWFYSBG/graph.json","events_json":"https://pith.science/api/pith-number/WDJHNYJGLEXKLW4UBL2KWFYSBG/events.json","paper":"https://pith.science/paper/WDJHNYJG"},"agent_actions":{"view_html":"https://pith.science/pith/WDJHNYJGLEXKLW4UBL2KWFYSBG","download_json":"https://pith.science/pith/WDJHNYJGLEXKLW4UBL2KWFYSBG.json","view_paper":"https://pith.science/paper/WDJHNYJG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26725&json=true","fetch_graph":"https://pith.science/api/pith-number/WDJHNYJGLEXKLW4UBL2KWFYSBG/graph.json","fetch_events":"https://pith.science/api/pith-number/WDJHNYJGLEXKLW4UBL2KWFYSBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WDJHNYJGLEXKLW4UBL2KWFYSBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WDJHNYJGLEXKLW4UBL2KWFYSBG/action/storage_attestation","attest_author":"https://pith.science/pith/WDJHNYJGLEXKLW4UBL2KWFYSBG/action/author_attestation","sign_citation":"https://pith.science/pith/WDJHNYJGLEXKLW4UBL2KWFYSBG/action/citation_signature","submit_replication":"https://pith.science/pith/WDJHNYJGLEXKLW4UBL2KWFYSBG/action/replication_record"}},"created_at":"2026-05-27T01:06:09.396361+00:00","updated_at":"2026-05-27T01:06:09.396361+00:00"}