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

In this work, we present QuickSRNet, an efficient super-resolutionarchitecture for real-time applications on mobile platforms. Super-resolutionclarifies, sharpens, and upscales an image to higher resolution. Applicationssuch as gaming and video playback along with the ever-improving displaycapabilities of TVs, smartphones, and VR headsets are driving the need forefficient upscaling solutions. While existing deep learning-basedsuper-resolution approaches achieve impressive results in terms of visualquality, enabling real-time DL-based super-resolution on mobile devices withcompute, thermal, and power constraints is challenging. To address thesechallenges, we propose QuickSRNet, a simple yet effective architecture thatprovides better accuracy-to-latency trade-offs than existing neuralarchitectures for single-image super resolution. We present training tricks tospeed up existing residual-based super-resolution architectures whilemaintaining robustness to quantization. Our proposed architecture produces1080p outputs via 2x upscaling in 2.2 ms on a modern smartphone, making itideal for high-fps real-time applications.

QuickSRNet: Plain Single-Image Super-Resolution Architecture for Faster Inference on Mobile Platforms