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 recent years, self-supervised methods for monocular depth estimation hasrapidly become an significant branch of depth estimation task, especially forautonomous driving applications. Despite the high overall precision achieved,current methods still suffer from a) imprecise object-level depth inference andb) uncertain scale factor. The former problem would cause texture copy orprovide inaccurate object boundary, and the latter would require currentmethods to have an additional sensor like LiDAR to provide depth ground-truthor stereo camera as additional training inputs, which makes them difficult toimplement. In this work, we propose to address these two problems together byintroducing DNet. Our contributions are twofold: a) a novel dense connectedprediction (DCP) layer is proposed to provide better object-level depthestimation and b) specifically for autonomous driving scenarios, densegeometrical constrains (DGC) is introduced so that precise scale factor can berecovered without additional cost for autonomous vehicles. Extensiveexperiments have been conducted and, both DCP layer and DGC module are provedto be effectively solving the aforementioned problems respectively. Thanks toDCP layer, object boundary can now be better distinguished in the depth map andthe depth is more continues on object level. It is also demonstrated that theperformance of using DGC to perform scale recovery is comparable to that usingground-truth information, when the camera height is given and the ground pointtakes up more than 1.03\% of the pixels. Code is available athttps://github.com/TJ-IPLab/DNet.

Toward Hierarchical Self-Supervised Monocular Absolute Depth Estimation for Autonomous Driving Applications