Temporal Event Stereo via Joint Learning with Stereoscopic Flow

TL;DR

This paper introduces a novel temporal event stereo framework that leverages joint learning with stereoscopic flow to improve 3D perception in event cameras, achieving state-of-the-art results efficiently.

Contribution

It proposes a new joint learning framework for temporal event stereo and stereoscopic flow, utilizing disparity-based training without ground truth optical flow.

Findings

Achieved state-of-the-art performance on MVSEC and DSEC datasets.

Enhanced stereo matching accuracy through temporal information aggregation.

Efficient computation via cascading previous information.

Abstract

Event cameras are dynamic vision sensors inspired by the biological retina, characterized by their high dynamic range, high temporal resolution, and low power consumption. These features make them capable of perceiving 3D environments even in extreme conditions. Event data is continuous across the time dimension, which allows a detailed description of each pixel's movements. To fully utilize the temporally dense and continuous nature of event cameras, we propose a novel temporal event stereo, a framework that continuously uses information from previous time steps. This is accomplished through the simultaneous training of an event stereo matching network alongside stereoscopic flow, a new concept that captures all pixel movements from stereo cameras. Since obtaining ground truth for optical flow during training is challenging, we propose a method that uses only disparity maps to train the stereoscopic flow. The performance of event-based stereo matching is enhanced by temporally aggregating information using the flows. We have achieved state-of-the-art performance on the MVSEC and the DSEC datasets. The method is computationally efficient, as it stacks previous information in a cascading manner. The code is available at https://github.com/mickeykang16/TemporalEventStereo.