Joint Alignment and Denoising for Event-Based Vision Sensors Using Regret-based Pareto Optimization

TL;DR

This paper introduces a joint optimization approach for event alignment and denoising in event-based vision sensors, addressing the limitations of separate processing modules.

Contribution

It formulates a bi-objective Pareto optimization problem to simultaneously improve event alignment and denoising using a contrast map and regret strategy.

Findings

Improved denoising and motion estimation performance

Effective joint optimization of alignment and denoising

Outperforms alternative methods in experiments

Abstract

This paper proposes a joint alignment and denoising method for event-based vision sensors (EVSs). Existing signal processing methods for EVSs typically perform event alignment (EA) and event denoising (ED) as separate modules. However, this separation creates a dilemma: without ED, EA is biased by noise, whereas without EA, ED struggles to distinguish signal events from noise ones. To address this dilemma, we jointly optimize EA and ED by formulating a bi-objective Pareto optimization problem. Our formulation is built upon a contrast map that counts the number of events localized in each pixel. With a contrast map, we can formulate EA as maximizing its variance and ED as minimizing the variance. We cast these two conflicting problems as a Pareto optimization and use a regret strategy to obtain a solution. Experimental results on denoising and motion estimation demonstrate that our method achieves improvements against alternative ones.