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

Depth perception is paramount to tackle real-world problems, ranging fromautonomous driving to consumer applications. For the latter, depth estimationfrom a single image represents the most versatile solution, since a standardcamera is available on almost any handheld device. Nonetheless, two main issueslimit its practical deployment: i) the low reliability when deployedin-the-wild and ii) the demanding resource requirements to achieve real-timeperformance, often not compatible with such devices. Therefore, in this paper,we deeply investigate these issues showing how they are both addressableadopting appropriate network design and training strategies -- also outlininghow to map the resulting networks on handheld devices to achieve real-timeperformance. Our thorough evaluation highlights the ability of such fastnetworks to generalize well to new environments, a crucial feature required totackle the extremely varied contexts faced in real applications. Indeed, tofurther support this evidence, we report experimental results concerningreal-time depth-aware augmented reality and image blurring with smartphonesin-the-wild.

Real-time single image depth perception in the wild with handheld devices