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/

Zendy Plus

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

Zendy Tools

Zendy Open

High dynamic range (HDR) imaging is still a challenging task in moderndigital photography. Recent research proposes solutions that providehigh-quality acquisition but at the cost of a very large number of operationsand a slow inference time that prevent the implementation of these solutions onlightweight real-time systems. In this paper, we propose CEN-HDR, a newcomputationally efficient neural network by providing a novel architecturebased on a light attention mechanism and sub-pixel convolution operations forreal-time HDR imaging. We also provide an efficient training scheme by applyingnetwork compression using knowledge distillation. We performed extensivequalitative and quantitative comparisons to show that our approach producescompetitive results in image quality while being faster than state-of-the-artsolutions, allowing it to be practically deployed under real-time constraints.Experimental results show our method obtains a score of 43.04 mu-PSNR on theKalantari2017 dataset with a framerate of 33 FPS using a Macbook M1 NPU.

CEN-HDR: Computationally Efficient neural Network for real-time High Dynamic Range imaging