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

Spherical images taken in all directions (360 degrees) allow representing thesurroundings of the subject and the space itself, providing an immersiveexperience to the viewers. Generating a spherical image from a singlenormal-field-of-view (NFOV) image is convenient and considerably expands theusage scenarios because there is no need to use a specific panoramic camera ortake images from multiple directions; however, it is still a challenging andunsolved problem. The primary challenge is controlling the high degree offreedom involved in generating a wide area that includes the all directions ofthe desired plausible spherical image. On the other hand, scene symmetry is abasic property of the global structure of the spherical images, such asrotation symmetry, plane symmetry and asymmetry. We propose a method togenerate spherical image from a single NFOV image, and control the degree offreedom of the generated regions using scene symmetry. We incorporatescene-symmetry parameters as latent variables into conditional variationalautoencoders, following which we learn the conditional probability of sphericalimages for NFOV images and scene symmetry. Furthermore, the probability densityfunctions are represented using neural networks, and scene symmetry isimplemented using both circular shift and flip of the hidden variables. Ourexperiments show that the proposed method can generate various plausiblespherical images, controlled from symmetric to asymmetric.

Spherical Image Generation from a Single Normal Field of View Image by Considering Scene Symmetry