Search papers, labs, and topics across Lattice.
This paper introduces Oriented Distance Field Motion Estimation (ODF Motion Estimation), a novel approach that replaces traditional iterative optimization with a single averaging step over precomputed event distance vectors, enhancing the speed and efficiency of motion estimation. The method achieves sub-pixel accuracy with the lowest latency compared to existing techniques, validated across both public and self-collected datasets. Additionally, ODF is applied to two downstream tasks: real-time non-blind image deblurring and low-power tracking, demonstrating its versatility and effectiveness in practical applications.
Achieving sub-pixel accuracy with the lowest latency, ODF Motion Estimation transforms event-based motion tasks while enabling real-time applications like image deblurring and efficient tracking.
Event-based motion estimation is central to tasks that demand high temporal resolution and robustness to fast motion. Existing methods typically rely on iterative optimization or repeated hypothesis comparison, offsetting the sensor's low-latency advantage. We propose Oriented Distance Field Motion Estimation (ODF Motion Estimation), which replaces this optimization with a single averaging step over a precomputed field of event distance vectors, combined with an adaptive event-count selection strategy and a parameter-free trail filter. On public and self-collected datasets, ODF motion estimation reaches sub-pixel accuracy at the lowest latency among compared methods. We validate its generality on two downstream applications rather than treating them as separate contributions. First, the estimated trajectory is converted into a blur kernel and paired with a compact iterative-unfolding network, trained on simulated motion-estimation noise, for real-time non-blind image deblurring, attaining competitive or superior PSNR/SSIM with under 1M parameters. Second, the same precomputed field is repurposed for directional event filtering in a low-power asynchronous pupil and glint tracker, sustaining stable tracking for tens of seconds while lowering a near-eye module's power draw.
