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

In the current monocular depth research, the dominant approach is to employunsupervised training on large datasets, driven by warped photometricconsistency. Such approaches lack robustness and are unable to generalize tochallenging domains such as nighttime scenes or adverse weather conditionswhere assumptions about photometric consistency break down.  We propose DeFeat-Net (Depth & Feature network), an approach tosimultaneously learn a cross-domain dense feature representation, alongside arobust depth-estimation framework based on warped feature consistency. Theresulting feature representation is learned in an unsupervised manner with noexplicit ground-truth correspondences required.  We show that within a single domain, our technique is comparable to both thecurrent state of the art in monocular depth estimation and supervised featurerepresentation learning. However, by simultaneously learning features, depthand motion, our technique is able to generalize to challenging domains,allowing DeFeat-Net to outperform the current state-of-the-art with around 10%reduction in all error measures on more challenging sequences such as nighttimedriving.

DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning