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 this paper, a new deep learning architecture for stereo disparityestimation is proposed. The proposed atrous multiscale network (AMNet) adoptsan efficient feature extractor with depthwise-separable convolutions and anextended cost volume that deploys novel stereo matching costs on the deepfeatures. A stacked atrous multiscale network is proposed to aggregate richmultiscale contextual information from the cost volume which allows forestimating the disparity with high accuracy at multiple scales. AMNet can befurther modified to be a foreground-background aware network, FBA-AMNet, whichis capable of discriminating between the foreground and the background objectsin the scene at multiple scales. An iterative multitask learning method isproposed to train FBA-AMNet end-to-end. The proposed disparity estimationnetworks, AMNet and FBA-AMNet, show accurate disparity estimates and advancethe state of the art on the challenging Middlebury, KITTI 2012, KITTI 2015, andSceneflow stereo disparity estimation benchmarks.

AMNet: Deep Atrous Multiscale Stereo Disparity Estimation Networks