NeuroLiDAR: Adaptive Frame Rate Depth Sensing via Neuromorphic Event-LiDAR Fusion

2026-05-16

AI Summary

This work addresses the inherent hardware trade-offs among frame rate, ranging distance, and spatial resolution that limit conventional LiDAR systems in capturing highly dynamic scenes. To overcome these limitations, the authors propose an adaptive depth perception framework that fuses sparse LiDAR measurements with dense neuromorphic event camera data. By introducing an event-driven keyframe detection mechanism and an event-guided depth extrapolation strategy, the method achieves, for the first time, dynamic and adaptive enhancement of LiDAR frame rates. Experimental evaluation on the authors’ newly curated ELiDAR dataset demonstrates a 29% reduction in RMSE for depth reconstruction, with effective frame rates adaptively increased to 27.8–47.3 Hz and peaking at 66 Hz.

Abstract

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 components: event-based keyframe detection and event-guided depth extrapolation, to dynamically adjust the sensing rate in response to scene dynamics. To evaluate our approach, we introduce ELiDAR, a dataset spanning outdoor and indoor scenarios, and show that NeuroLiDAR reduces depth reconstruction error by $\approx$29\% in RMSE while achieving adaptive frame rates between 27.8-47.3 Hz. Our code and dataset are available at https://github.com/darshanakgr/neurolidar.

Problem

• LiDAR
• frame rate
• depth reconstruction
• scene dynamics
• hardware constraints

Innovation

• Neuromorphic Vision
• Event Camera
• LiDAR Fusion
• Adaptive Frame Rate
• Depth Reconstruction