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

In this paper, we present Shift Convolution Network (ShiftConvNet) to providematching capability between two feature maps for stereo estimation. Theproposed method can speedily produce a highly accurate disparity map fromstereo images. A module called shift convolution layer is proposed to replacethe traditional correlation layer to perform patch comparisons between twofeature maps. By using a novel architecture of convolutional network to learnthe matching process, ShiftConvNet can produce better results thanDispNet-C[1], also running faster with 5 fps. Moreover, with a proposed autoshift convolution refine part, further improvement is obtained. The proposedapproach was evaluated on FlyingThings 3D. It achieves state-of-the-art resultson the benchmark dataset. Codes will be made available at github.

Shift Convolution Network for Stereo Matching