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 deep learning-based local stereo matching methods, larger image patchesusually bring better stereo matching accuracy. However, it is unrealistic toincrease the size of the image patch size without restriction. Arbitrarilyextending the patch size will change the local stereo matching method into theglobal stereo matching method, and the matching accuracy will be saturated. Wesimplified the existing Siamese convolutional network by reducing the number ofnetwork parameters and propose an efficient CNN based structure, namelyAdaptive Deconvolution-based disparity matching Net (ADSM net) by addingdeconvolution layers to learn how to enlarge the size of input feature map forthe following convolution layers. Experimental results on the KITTI 2012 and2015 datasets demonstrate that the proposed method can achieve a good trade-offbetween accuracy and complexity.

Adaptive Deconvolution-based stereo matching Net for Local Stereo Matching