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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Motivated by the need to identify erroneous disparity assignments, variousapproaches for uncertainty and confidence estimation of dense stereo matchinghave been presented in recent years. As in many other fields, especially deeplearning based methods have shown convincing results. However, most of thesemethods only model the uncertainty contained in the data, while ignoring theuncertainty of the employed dense stereo matching procedure. Additionallymodelling the latter, however, is particularly beneficial if the domain of thetraining data varies from that of the data to be processed. For this purpose,in the present work the idea of probabilistic deep learning is applied to thetask of dense stereo matching for the first time. Based on the well-known andcommonly employed GC-Net architecture, a novel probabilistic neural network ispresented, for the task of joint depth and uncertainty estimation from epipolarrectified stereo image pairs. Instead of learning the network parametersdirectly, the proposed probabilistic neural network learns a probabilitydistribution from which parameters are sampled for every prediction. Thevariations between multiple such predictions on the same image pair allow toapproximate the model uncertainty. The quality of the estimated depth anduncertainty information is assessed in an extensive evaluation on threedifferent datasets.

Uncertainty Estimation for End-To-End Learned Dense Stereo Matching via Probabilistic Deep Learning