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

Recently, end-to-end trainable deep neural networks have significantlyimproved stereo depth estimation for perspective images. However, 360{\deg}images captured under equirectangular projection cannot benefit from directlyadopting existing methods due to distortion introduced (i.e., lines in 3D arenot projected onto lines in 2D). To tackle this issue, we present a novelarchitecture specifically designed for spherical disparity using the setting oftop-bottom 360{\deg} camera pairs. Moreover, we propose to mitigate thedistortion issue by (1) an additional input branch capturing the position andrelation of each pixel in the spherical coordinate, and (2) a cost volume builtupon a learnable shifting filter. Due to the lack of 360{\deg} stereo data, wecollect two 360{\deg} stereo datasets from Matterport3D and Stanford3D fortraining and evaluation. Extensive experiments and ablation study are providedto validate our method against existing algorithms. Finally, we show promisingresults on real-world environments capturing images with two consumer-levelcameras.

360SD-Net: 360{\deg} Stereo Depth Estimation with Learnable Cost Volume