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 new loss function for joint disparity and uncertainty estimationin deep stereo matching. Our work is motivated by the need for preciseuncertainty estimates and the observation that multi-task learning often leadsto improved performance in all tasks. We show that this can be achieved byrequiring the distribution of uncertainty to match the distribution ofdisparity errors via a KL divergence term in the network's loss function. Adifferentiable soft-histogramming technique is used to approximate thedistributions so that they can be used in the loss. We experimentally assessthe effectiveness of our approach and observe significant improvements in bothdisparity and uncertainty prediction on large datasets.

Learning the Distribution of Errors in Stereo Matching for Joint Disparity and Uncertainty Estimation