Motion-aware Event Suppression for Event Cameras

TL;DR

This paper presents a real-time, lightweight framework for motion-aware event suppression in event cameras, improving segmentation accuracy, inference speed, and benefits downstream vision tasks like odometry and token pruning.

Contribution

The authors introduce the first motion-aware event suppression framework that jointly segments IMOs and predicts their motion, enabling anticipatory filtering in real time.

Findings

Outperforms previous methods with 67% higher segmentation accuracy on EVIMO.

Operates at 173 Hz inference rate with less than 1 GB memory.

Accelerates vision transformer inference by 83% and reduces odometry error by 13%.

Abstract

In this work, we introduce the first framework for Motion-aware Event Suppression, which learns to filter events triggered by IMOs and ego-motion in real time. Our model jointly segments IMOs in the current event stream while predicting their future motion, enabling anticipatory suppression of dynamic events before they occur. Our lightweight architecture achieves 173 Hz inference on consumer-grade GPUs with less than 1 GB of memory usage, outperforming previous state-of-the-art methods on the challenging EVIMO benchmark by 67\% in segmentation accuracy while operating at a 53\% higher inference rate. Moreover, we demonstrate significant benefits for downstream applications: our method accelerates Vision Transformer inference by 83\% via token pruning and improves event-based visual odometry accuracy, reducing Absolute Trajectory Error (ATE) by 13\%.