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

We present a generalised self-supervised learning approach for monocularestimation of the real depth across scenes with diverse depth ranges from1--100s of meters. Existing supervised methods for monocular depth estimationrequire accurate depth measurements for training. This limitation has led tothe introduction of self-supervised methods that are trained on stereo imagepairs with a fixed camera baseline to estimate disparity which is transformedto depth given known calibration. Self-supervised approaches have demonstratedimpressive results but do not generalise to scenes with different depth rangesor camera baselines. In this paper, we introduce RealMonoDepth aself-supervised monocular depth estimation approach which learns to estimatethe real scene depth for a diverse range of indoor and outdoor scenes. A novelloss function with respect to the true scene depth based on relative depthscaling and warping is proposed. This allows self-supervised training of asingle network with multiple data sets for scenes with diverse depth rangesfrom both stereo pair and in the wild moving camera data sets. A comprehensiveperformance evaluation across five benchmark data sets demonstrates thatRealMonoDepth provides a single trained network which generalises depthestimation across indoor and outdoor scenes, consistently outperformingprevious self-supervised approaches.

RealMonoDepth: Self-Supervised Monocular Depth Estimation for General Scenes