{"paper":{"title":"NeuroLiDAR: Adaptive Frame Rate Depth Sensing via Neuromorphic Event-LiDAR Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"NeuroLiDAR fuses event camera streams with sparse LiDAR scans to raise effective depth frame rates to around 66 Hz while cutting reconstruction error by 29 percent.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Archan Misra, Darshana Rathnayake, Dulanga Weerakoon, Meera Radhakrishnan","submitted_at":"2026-05-16T04:21:59Z","abstract_excerpt":"LiDARs are widely used for 3D depth reconstruction, but their performance is often limited by inherent hardware constraints that impose trade-offs between range, spatial resolution, and frame rate. Many LiDAR systems typically operate at low frame rates (e.g., 5-10 Hz), prioritizing long-range sensing over responsiveness to rapid scene changes. We present NeuroLiDAR, an adaptive depth sensing framework that achieves effective frame rates of up to $\\approx$66 Hz by fusing temporally sparse LiDAR data with temporally dense inputs from neuromorphic event cameras. NeuroLiDAR integrates two compone"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"NeuroLiDAR achieves effective frame rates of up to ≈66 Hz by fusing temporally sparse LiDAR data with temporally dense inputs from neuromorphic event cameras, reducing depth reconstruction error by ≈29% in RMSE while achieving adaptive frame rates between 27.8-47.3 Hz.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Event-based keyframe detection and event-guided depth extrapolation can reliably adapt the LiDAR sensing rate across varied indoor and outdoor scenes without introducing large extrapolation errors or missing critical motion.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"NeuroLiDAR adaptively boosts LiDAR frame rates to 27.8-66 Hz via event-camera fusion and cuts depth RMSE by 29% on a new ELiDAR dataset.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"NeuroLiDAR fuses event camera streams with sparse LiDAR scans to raise effective depth frame rates to around 66 Hz while cutting reconstruction error by 29 percent.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9cfe7c25caa7ff34c6c117d37c6c1e884861be3fdb2834ec44019fc2121faac2"},"source":{"id":"2605.16805","kind":"arxiv","version":1},"verdict":{"id":"aac51cd5-53c1-4097-86e2-b530eeb4b03f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T21:11:40.154163Z","strongest_claim":"NeuroLiDAR achieves effective frame rates of up to ≈66 Hz by fusing temporally sparse LiDAR data with temporally dense inputs from neuromorphic event cameras, reducing depth reconstruction error by ≈29% in RMSE while achieving adaptive frame rates between 27.8-47.3 Hz.","one_line_summary":"NeuroLiDAR adaptively boosts LiDAR frame rates to 27.8-66 Hz via event-camera fusion and cuts depth RMSE by 29% on a new ELiDAR dataset.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Event-based keyframe detection and event-guided depth extrapolation can reliably adapt the LiDAR sensing rate across varied indoor and outdoor scenes without introducing large extrapolation errors or missing critical motion.","pith_extraction_headline":"NeuroLiDAR fuses event camera streams with sparse LiDAR scans to raise effective depth frame rates to around 66 Hz while cutting reconstruction error by 29 percent."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16805/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T21:31:19.291225Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T21:21:18.480907Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T19:01:56.283530Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.420716Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"ff28706c41f7e6aa1c08de093b7b4844f6df3727009417453e6bbd1ce9d4b8e6"},"references":{"count":26,"sample":[{"doi":"","year":2022,"title":"Event-based vision: A survey,","work_id":"2a660643-4e02-4e2d-abcc-59204de3af80","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Event-Based Frame Interpolation with Ad-hoc Deblurring","work_id":"c18075f9-98ba-43dd-9577-2b51b5c24b3b","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Combining events and frames using recurrent asynchronous multimodal networks for monocular depth prediction,","work_id":"6b0c5135-ddd2-437a-bb35-324e8bfc40f0","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Dense depth- map estimation based on fusion of event camera and sparse lidar,","work_id":"ea0acb56-a844-4736-9ba9-5a3c1efc727d","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Learning spatial- temporal implicit neural representations for event-guided video super- resolution,","work_id":"38379fee-747e-4e8a-b503-88f79a7f75a4","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":26,"snapshot_sha256":"2c0e787c740d9f25019306caae197875488361903939eaf6b7c7666e1a3baeee","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"97f347d33bdb7255625e532f4ace6dbde859376400c37a22c07af9cfa1a23e97"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}