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

Despite advancements in self-supervised monocular depth estimation,challenges persist in dynamic scenarios due to the dependence on assumptionsabout a static world. In this paper, we present MGDepth, a Motion-Guided CostVolume Depth Net, to achieve precise depth estimation for both dynamic objectsand static backgrounds, all while maintaining computational efficiency. Totackle the challenges posed by dynamic content, we incorporate optical flow andcoarse monocular depth to create a novel static reference frame. This frame isthen utilized to build a motion-guided cost volume in collaboration with thetarget frame. Additionally, to enhance the accuracy and resilience of thenetwork structure, we introduce an attention-based depth net architecture toeffectively integrate information from feature maps with varying resolutions.Compared to methods with similar computational costs, MGDepth achieves asignificant reduction of approximately seven percent in root-mean-square errorfor self-supervised monocular depth estimation on the KITTI-2015 dataset.

MGDepth: Motion-Guided Cost Volume For Self-Supervised Monocular Depth In Dynamic Scenarios