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 deep generative models have achieved impressive progress in modelingthe distribution of training data. In this work, we present for the first timea generative model for 4D light field patches using variational autoencoders tocapture the data distribution of light field patches. We develop a generativemodel conditioned on the central view of the light field and incorporate thisas a prior in an energy minimization framework to address diverse light fieldreconstruction tasks. While pure learning-based approaches do achieve excellentresults on each instance of such a problem, their applicability is limited tothe specific observation model they have been trained on. On the contrary, ourtrained light field generative model can be incorporated as a prior into anymodel-based optimization approach and therefore extend to diversereconstruction tasks including light field view synthesis, spatial-angularsuper resolution and reconstruction from coded projections. Our proposed methoddemonstrates good reconstruction, with performance approaching end-to-endtrained networks, while outperforming traditional model-based approaches onboth synthetic and real scenes. Furthermore, we show that our approach enablesreliable light field recovery despite distortions in the input.

A Generative Model for Generic Light Field Reconstruction