Event Collapse in Contrast Maximization Frameworks
This addresses a specific issue in event-based vision for researchers, offering a novel solution to improve accuracy in tasks like ego-motion estimation, though it is incremental as it builds on existing frameworks.
The paper tackles the problem of event collapse in contrast maximization frameworks for event-based computer vision, proposing metrics based on differential geometry and physics to mitigate it, and shows experimentally that these metrics effectively reduce collapse without harming well-posed warps.
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.