Event Collapse in Contrast Maximization Frameworks

TL;DR

This paper analyzes the phenomenon of event collapse in contrast maximization frameworks for event-based vision, proposing new metrics based on differential geometry that effectively mitigate collapse without harming well-posed warps.

Contribution

It introduces collapse metrics derived from first principles to detect and mitigate event collapse, providing the first effective regularizers for this issue in contrast maximization.

Findings

Proposed metrics successfully mitigate event collapse in experiments.

Regularizers based on these metrics outperform prior work.

Metrics do not negatively impact well-posed warps.

Abstract

Contrast maximization (CMax) is a framework that provides state-of-the-art results on several event-based computer vision tasks, such as ego-motion or optical flow estimation. However, it may suffer from a problem called event collapse, which is an undesired solution where events are warped into too few pixels. As prior works have largely ignored the issue or proposed workarounds, it is imperative to analyze this phenomenon in detail. Our work demonstrates event collapse in its simplest form and proposes collapse metrics by using first principles of space-time deformation based on differential geometry and physics. We experimentally show on publicly available datasets that the proposed metrics mitigate event collapse and do not harm well-posed warps. To the best of our knowledge, regularizers based on the proposed metrics are the only effective solution against event collapse in the experimental settings considered, compared with other methods. We hope that this work inspires further research to tackle more complex warp models.