{"paper":{"title":"FS-I2P:A Hierarchical Focus-Sweep Registration Network with Dynamically Allocated Depth","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A focus-sweep interaction module with dynamic depth allocation improves cross-modal image-to-point cloud registration by cutting attention drift.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoqun Yin, Bohao Liao, Tianzhu Zhang, Xiaotian Yin, Xujing Tao, Yujia Chen, Zhixin Cheng","submitted_at":"2026-05-08T11:33:18Z","abstract_excerpt":"Image-to-point cloud registration is often challenged by viewpoint changes, cross-modal discrepancies, and repetitive textures, which induce scale ambiguity and consequently lead to erroneous correspondences. Recent detection-free methods alleviate this issue by leveraging multi-scale features and transformer-based interactions. However, they still suffer from attention drift across layers and intra-scale inconsistencies, hindering precise registration. Inspired by human behavior, we propose a ``Focus--Sweep'' paradigm and develop a Hierarchical Focus--Sweep Interaction Module within an SSM-ba"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Extensive experiments and ablations on two benchmarks, RGB-D Scenes V2 and 7-Scenes, demonstrate that our approach achieves state-of-the-art performance.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The Hierarchical Focus-Sweep Interaction Module and Dynamic Layer Allocation Strategy actually reduce attention drift and intra-scale inconsistencies enough to produce the claimed registration gains.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"FS-I2P uses a focus-sweep paradigm and dynamic layer allocation in an SSM framework to achieve state-of-the-art image-to-point cloud registration on RGB-D Scenes V2 and 7-Scenes benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A focus-sweep interaction module with dynamic depth allocation improves cross-modal image-to-point cloud registration by cutting attention drift.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"18b09be97840492ad3974f802a476bc0646a5c1dd4899d41bb7d82518cd770dc"},"source":{"id":"2605.07607","kind":"arxiv","version":2},"verdict":{"id":"e8d0b487-3dc2-4e3e-9e37-c0680c3a8e89","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T02:17:28.247352Z","strongest_claim":"Extensive experiments and ablations on two benchmarks, RGB-D Scenes V2 and 7-Scenes, demonstrate that our approach achieves state-of-the-art performance.","one_line_summary":"FS-I2P uses a focus-sweep paradigm and dynamic layer allocation in an SSM framework to achieve state-of-the-art image-to-point cloud registration on RGB-D Scenes V2 and 7-Scenes benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The Hierarchical Focus-Sweep Interaction Module and Dynamic Layer Allocation Strategy actually reduce attention drift and intra-scale inconsistencies enough to produce the claimed registration gains.","pith_extraction_headline":"A focus-sweep interaction module with dynamic depth allocation improves cross-modal image-to-point cloud registration by cutting attention drift."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.07607/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T10:42:02.802033Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-20T05:38:24.144516Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T16:01:18.972898Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T11:40:41.503334Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"4cbd5093c8c06102aa71a059de5a5f399ddb9965064894a0bd0ec1fd65b468e1"},"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"}