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

Imaging under photon-scarce situations introduces challenges to manyapplications as the captured images are with low signal-to-noise ratio and poorluminance. In this paper, we investigate the raw image restoration underlow-photon-count conditions by simulating the imaging of quanta image sensor(QIS). We develop a lightweight framework, which consists of a multi-levelpyramid denoising network (MPDNet) and a luminance adjustment (LA) module toachieve separate denoising and luminance enhancement. The main component of ourframework is the multi-skip attention residual block (MARB), which integratesmulti-scale feature fusion and attention mechanism for better featurerepresentation. Our MPDNet adopts the idea of Laplacian pyramid to learn thesmall-scale noise map and larger-scale high-frequency details at differentlevels, and feature extractions are conducted on the multi-scale input imagesto encode richer contextual information. Our LA module enhances the luminanceof the denoised image by estimating its illumination, which can better avoidcolor distortion. Extensive experimental results have demonstrated that ourimage restorer can achieve superior performance on the degraded images withvarious photon levels by suppressing noise and recovering luminance and coloreffectively.

An Effective Image Restorer: Denoising and Luminance Adjustment for Low-photon-count Imaging