English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Accurately perceiving location and scene is crucial for autonomous drivingand mobile robots. Recent advances in deep learning have made it possible tolearn egomotion and depth from monocular images in a self-supervised manner,without requiring highly precise labels to train the networks. However,monocular vision methods suffer from a limitation known as scale-ambiguity,which restricts their application when absolute-scale is necessary. To addressthis, we propose SelfOdom, a self-supervised dual-network framework that canrobustly and consistently learn and generate pose and depth estimates in globalscale from monocular images. In particular, we introduce a novel coarse-to-finetraining strategy that enables the metric scale to be recovered in a two-stageprocess. Furthermore, SelfOdom is flexible and can incorporate inertial datawith images, which improves its robustness in challenging scenarios, using anattention-based fusion module. Our model excels in both normal and challenginglighting conditions, including difficult night scenes. Extensive experiments onpublic datasets have demonstrated that SelfOdom outperforms representativetraditional and learning-based VO and VIO models.

SelfOdom: Self-supervised Egomotion and Depth Learning via Bi-directional Coarse-to-Fine Scale Recovery