A Fast Geometric Regularizer to Mitigate Event Collapse in the Contrast Maximization Framework

TL;DR

This paper introduces a fast, geometry-based regularizer for contrast maximization in event cameras, effectively reducing event collapse and improving accuracy without increasing computational costs.

Contribution

A novel, efficient geometric regularizer is proposed to mitigate event collapse in contrast maximization, outperforming prior methods in speed and effectiveness.

Findings

Achieves state-of-the-art accuracy in motion estimation.

Reduces computational complexity by 2-4 times.

The regularizer is the only effective solution without runtime trade-offs.

Abstract

Event cameras are emerging vision sensors and their advantages are suitable for various applications such as autonomous robots. Contrast maximization (CMax), which provides state-of-the-art accuracy on motion estimation using events, may suffer from an overfitting problem called event collapse. Prior works are computationally expensive or cannot alleviate the overfitting, which undermines the benefits of the CMax framework. We propose a novel, computationally efficient regularizer based on geometric principles to mitigate event collapse. The experiments show that the proposed regularizer achieves state-of-the-art accuracy results, while its reduced computational complexity makes it two to four times faster than previous approaches. To the best of our knowledge, our regularizer is the only effective solution for event collapse without trading off runtime. We hope our work opens the door for future applications that unlocks the advantages of event cameras.