MBA-VO: Motion Blur Aware Visual Odometry

TL;DR

This paper introduces a hybrid visual odometry method that explicitly models motion blur caused by camera movement during exposure, improving robustness in low-light conditions while maintaining accuracy.

Contribution

It presents a novel direct approach for motion blur-aware visual odometry and introduces a new benchmarking dataset for this problem.

Findings

Improved robustness of visual odometry under motion blur conditions.

Maintained comparable accuracy to blur-free images.

Demonstrated effectiveness on a new motion blur dataset.

Abstract

Motion blur is one of the major challenges remaining for visual odometry methods. In low-light conditions where longer exposure times are necessary, motion blur can appear even for relatively slow camera motions. In this paper we present a novel hybrid visual odometry pipeline with direct approach that explicitly models and estimates the camera's local trajectory within the exposure time. This allows us to actively compensate for any motion blur that occurs due to the camera motion. In addition, we also contribute a novel benchmarking dataset for motion blur aware visual odometry. In experiments we show that by directly modeling the image formation process, we are able to improve robustness of the visual odometry, while keeping comparable accuracy as that for images without motion blur.