Dynamic Receptive Field Generation for Full-Reference Image Quality Assessment

Most full-reference image quality assessment (FR-IQA) methods advanced to date have been holistically designed without regard to the type of distortion impairing the image. However, the perception of distortion depends nonlinearly on the distortion type. Here we propose a novel FR-IQA framework that...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing 2020-01, Vol.29, p.4219-4231
Main Authors: Kim, Woojae, Nguyen, Anh-Duc, Lee, Sanghoon, Bovik, Alan Conrad
Format: Article
Language:English
Subjects:
Artificial neural networks
Computational modeling
convolutional neural networks (CNNs)
Distortion
dynamic filter networks (DFNs)
dynamic receptive fields (DRFs)
Full-reference image quality assessment (FR-IQA)
human visual system (HVS)
Image quality
Model accuracy
Nonlinear distortion
Quality assessment
Sensitivity
Streaming media
Visualization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Most full-reference image quality assessment (FR-IQA) methods advanced to date have been holistically designed without regard to the type of distortion impairing the image. However, the perception of distortion depends nonlinearly on the distortion type. Here we propose a novel FR-IQA framework that dynamically generates receptive fields responsive to distortion type. Our proposed method- dynamic receptive field generation based image quality assessor (DRF-IQA)-separates the process of FR-IQA into two streams: 1) dynamic error representation and 2) visual sensitivity-based quality pooling. The first stream generates dynamic receptive fields on the input distorted image, implemented by a trained convolutional neural network (CNN), then the generated receptive field profiles are convolved with the distorted and reference images, and differenced to produce spatial error maps. In the second stream, a visual sensitivity map is generated. The visual sensitivity map is used to weight the spatial error map. The experimental results show that the proposed model achieves state-of-the-art prediction accuracy on various open IQA databases.
ISSN:1057-7149
1941-0042
DOI:10.1109/TIP.2020.2968283