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

Image quality assessment (IQA) algorithm aims to quantify the humanperception of image quality. Unfortunately, there is a performance drop whenassessing the distortion images generated by generative adversarial network(GAN) with seemingly realistic texture. In this work, we conjecture that thismaladaptation lies in the backbone of IQA models, where patch-level predictionmethods use independent image patches as input to calculate their scoresseparately, but lack spatial relationship modeling among image patches.Therefore, we propose an Attention-based Hybrid Image Quality AssessmentNetwork (AHIQ) to deal with the challenge and get better performance on theGAN-based IQA task. Firstly, we adopt a two-branch architecture, including avision transformer (ViT) branch and a convolutional neural network (CNN) branchfor feature extraction. The hybrid architecture combines interactioninformation among image patches captured by ViT and local texture details fromCNN. To make the features from shallow CNN more focused on the visually salientregion, a deformable convolution is applied with the help of semanticinformation from the ViT branch. Finally, we use a patch-wise score predictionmodule to obtain the final score. The experiments show that our modeloutperforms the state-of-the-art methods on four standard IQA datasets and AHIQranked first on the Full Reference (FR) track of the NTIRE 2022 PerceptualImage Quality Assessment Challenge.

Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Network