Event Collapse in Contrast Maximization Frameworks

07/08/2022
by   Shintaro Shiba, et al.
0

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.

READ FULL TEXT

page 11

page 14

research
12/14/2022

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

Event cameras are emerging vision sensors and their advantages are suita...
research
04/04/2018

A Unifying Contrast Maximization Framework for Event Cameras, with Applications to Motion, Depth, and Optical Flow Estimation

We present a unifying framework to solve several computer vision problem...
research
12/23/2022

Fast Event-based Optical Flow Estimation by Triplet Matching

Event cameras are novel bio-inspired sensors that offer advantages over ...
research
03/09/2023

Taming Contrast Maximization for Learning Sequential, Low-latency, Event-based Optical Flow

Event cameras have recently gained significant traction since they open ...
research
09/09/2022

EDeNN: Event Decay Neural Networks for low latency vision

Despite the success of neural networks in computer vision tasks, digital...
research
04/27/2023

Density Invariant Contrast Maximization for Neuromorphic Earth Observations

Contrast maximization (CMax) techniques are widely used in event-based v...
research
11/24/2022

Lightweight Event-based Optical Flow Estimation via Iterative Deblurring

Inspired by frame-based methods, state-of-the-art event-based optical fl...

Please sign up or login with your details

Forgot password? Click here to reset