MBA-VO: Motion Blur Aware Visual Odometry
This addresses motion blur challenges in visual odometry, particularly in low-light conditions, but is incremental as it builds on existing direct methods.
The paper tackles motion blur in visual odometry by developing a hybrid pipeline that models and estimates the camera's trajectory during exposure to actively compensate for blur, resulting in improved robustness while maintaining accuracy comparable to blur-free images.
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.