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

Synthesizing a densely sampled light field from a single image is highlybeneficial for many applications. The conventional method reconstructs a depthmap and relies on physical-based rendering and a secondary network to improvethe synthesized novel views. Simple pixel-based loss also limits the network bymaking it rely on pixel intensity cue rather than geometric reasoning. In thisstudy, we show that a different geometric representation, namely, appearanceflow, can be used to synthesize a light field from a single image robustly anddirectly. A single end-to-end deep neural network that does not require aphysical-based approach nor a post-processing subnetwork is proposed. Two novelloss functions based on known light field domain knowledge are presented toenable the network to preserve the spatio-angular consistency betweensub-aperture images effectively. Experimental results show that the proposedmodel successfully synthesizes dense light fields and qualitatively andquantitatively outperforms the previous model . The method can be generalizedto arbitrary scenes, rather than focusing on a particular class of object. Thesynthesized light field can be used for various applications, such as depthestimation and refocusing.

Synthesizing a 4D Spatio-Angular Consistent Light Field from a Single Image