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

With the rapid development of AI hardware accelerators, applying deeplearning-based algorithms to solve various low-level vision tasks on mobiledevices has gradually become possible. However, two main problems still need tobe solved: task-specific algorithms make it difficult to integrate them into asingle neural network architecture, and large amounts of parameters make itdifficult to achieve real-time inference. To tackle these problems, we proposea novel network, SYENet, with only $~$6K parameters, to handle multiplelow-level vision tasks on mobile devices in a real-time manner. The SYENetconsists of two asymmetrical branches with simple building blocks. Toeffectively connect the results by asymmetrical branches, a QuadraticConnection Unit(QCU) is proposed. Furthermore, to improve performance, a newOutlier-Aware Loss is proposed to process the image. The proposed method provesits superior performance with the best PSNR as compared with other networks inreal-time applications such as Image Signal Processing(ISP), Low-LightEnhancement(LLE), and Super-Resolution(SR) with 2K60FPS throughput on Qualcomm8 Gen 1 mobile SoC(System-on-Chip). Particularly, for ISP task, SYENet got thehighest score in MAI 2022 Learned Smartphone ISP challenge.

SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-time Performance on Mobile Device