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

Unsupervised depth learning takes the appearance difference between a targetview and a view synthesized from its adjacent frame as supervisory signal.Since the supervisory signal only comes from images themselves, the resolutionof training data significantly impacts the performance. High-resolution imagescontain more fine-grained details and provide more accurate supervisory signal.However, due to the limitation of memory and computation power, the originalimages are typically down-sampled during training, which suffers heavy loss ofdetails and disparity accuracy. In order to fully explore the informationcontained in high-resolution data, we propose a simple yet effective dualnetworks architecture, which can directly take high-resolution images as inputand generate high-resolution and high-accuracy depth map efficiently. We alsopropose a Self-assembled Attention (SA-Attention) module to handle low-textureregion. The evaluation on the benchmark KITTI and Make3D datasets demonstratesthat our method achieves state-of-the-art results in the monocular depthestimation task.

Unsupervised High-Resolution Depth Learning From Videos With Dual Networks