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

Visual illusions are a very useful tool for vision scientists, because theyallow them to better probe the limits, thresholds and errors of the visualsystem. In this work we introduce the first ever framework to generate novelvisual illusions with an artificial neural network (ANN). It takes the form ofa generative adversarial network, with a generator of visual illusioncandidates and two discriminator modules, one for the inducer background andanother that decides whether or not the candidate is indeed an illusion. Thegenerality of the model is exemplified by synthesizing illusions of differenttypes, and validated with psychophysical experiments that corroborate that theoutputs of our ANN are indeed visual illusions to human observers. Apart fromsynthesizing new visual illusions, which may help vision researchers, theproposed model has the potential to open new ways to study the similarities anddifferences between ANN and human visual perception.

Synthesizing Visual Illusions Using Generative Adversarial Networks