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

Deep models have demonstrated recent success in single-image dehazing. Mostprior methods consider fully supervised training and learn from paired cleanand hazy images, where a hazy image is synthesized based on a clean image andits estimated depth map. This paradigm, however, can produce low-quality hazyimages due to inaccurate depth estimation, resulting in poor generalization ofthe trained models. In this paper, we explore an alternative approach forgenerating paired clean-hazy images by leveraging computer graphics. Using amodern game engine, our approach renders crisp clean images and their precisedepth maps, based on which high-quality hazy images can be synthesized fortraining dehazing models. To this end, we present SimHaze: a new synthetic hazedataset. More importantly, we show that training with SimHaze alone allows thelatest dehazing models to achieve significantly better performance incomparison to previous dehazing datasets. Our dataset and code will be madepublicly available.

SimHaze: game engine simulated data for real-world dehazing