{"paper":{"title":"3D-LENS: A 3D Lifting-based Elevated Novel-view Synthesis method for Single-View Aerial-Ground Re-Identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"3D mesh reconstruction from single views enables re-identification across unseen aerial and ground perspectives.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Astrid Sabourin, Catherine Achard, Guillaume Lapouge, William Grolleau","submitted_at":"2026-04-29T10:38:48Z","abstract_excerpt":"Aerial-Ground Re-Identification (AG-ReID) is constrained by the viewpoint-domain gap, as drastic viewpoint disparities occlude or distort discriminative features, making cross-viewpoint image retrieval challenging. While existing methods rely on paired cross-view annotations, real-world deployments, such as wilderness search-and-rescue (SAR), often lack target-domain data, requiring retrieval from ground-level references alone. To our knowledge, we are the first to address this challenge by formalizing the Single-View AG-ReID (SV AG-ReID) setting, where models trained on a single real viewpoin"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Extensive experiments demonstrate that our method achieves state-of-the-art performance on SV AG-ReID scenarios.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Large-scale 3D mesh reconstruction from single real viewpoints can produce geometrically consistent novel views across diverse categories without predefined templates, and synthetic-to-real bias can be sufficiently mitigated for effective generalization.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"3D-LENS formalizes single-view aerial-ground re-identification and uses 3D lifting for novel view synthesis plus bias-mitigating representation learning to achieve SOTA cross-view matching.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"3D mesh reconstruction from single views enables re-identification across unseen aerial and ground perspectives.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ee3f8e0d72860032de6f016e2672edfb4359dd7cb0e15c35b052b9f51d58821e"},"source":{"id":"2604.26520","kind":"arxiv","version":2},"verdict":{"id":"bb67d9ac-be07-456b-af69-0fb070aff4c5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T11:45:13.152932Z","strongest_claim":"Extensive experiments demonstrate that our method achieves state-of-the-art performance on SV AG-ReID scenarios.","one_line_summary":"3D-LENS formalizes single-view aerial-ground re-identification and uses 3D lifting for novel view synthesis plus bias-mitigating representation learning to achieve SOTA cross-view matching.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Large-scale 3D mesh reconstruction from single real viewpoints can produce geometrically consistent novel views across diverse categories without predefined templates, and synthetic-to-real bias can be sufficiently mitigated for effective generalization.","pith_extraction_headline":"3D mesh reconstruction from single views enables re-identification across unseen aerial and ground perspectives."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.26520/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T00:33:49.100351Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T20:03:32.537338Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"b9af7acc1481d4f969d9cf1548f6d11d6898de6a9bf295d247aa55250b95d0dc"},"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"}