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

360{\deg} images are widely available over the last few years. This paperproposes a new technique for single 360{\deg} image depth prediction under openenvironments. Depth prediction from a 360{\deg} single image is not easy fortwo reasons. One is the limitation of supervision datasets - the currentlyavailable dataset is limited to indoor scenes. The other is the problems causedby Equirectangular Projection Format (ERP), commonly used for 360{\deg} images,that are coordinate and distortion. There is only one method existing that usescube map projection to produce six perspective images and apply self-supervisedlearning using motion pictures for perspective depth prediction to deal withthese problems. Different from the existing method, we directly use the ERPformat. We propose a framework of direct use of ERP with coordinate conversionof correspondences and distortion-aware upsampling module to deal with the ERPrelated problems and extend a self-supervised learning method for openenvironments. For the experiments, we firstly built a dataset for theevaluation, and quantitatively evaluate the depth prediction in outdoor scenes.We show that it outperforms the state-of-the-art technique

Distortion-Aware Self-Supervised 360{\deg} Depth Estimation from A Single Equirectangular Projection Image