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

Recent deep monocular depth estimation approaches based on supervisedregression have achieved remarkable performance. However, they require costlyground truth annotations during training. To cope with this issue, in thispaper we present a novel unsupervised deep learning approach for predictingdepth maps. We introduce a new network architecture, named Progressive FusionNetwork (PFN), that is specifically designed for binocular stereo depthestimation. This network is based on a multi-scale refinement strategy thatcombines the information provided by both stereo views. In addition, we proposeto stack twice this network in order to form a cycle. This cycle approach canbe interpreted as a form of data-augmentation since, at training time, thenetwork learns both from the training set images (in the forward half-cycle)but also from the synthesized images (in the backward half-cycle). Thearchitecture is jointly trained with adversarial learning. Extensiveexperiments on the publicly available datasets KITTI, Cityscapes andApolloScape demonstrate the effectiveness of the proposed model which iscompetitive with other unsupervised deep learning methods for depth prediction.

Progressive Fusion for Unsupervised Binocular Depth Estimation using Cycled Networks