Deep Bi-directional Attention Network for Image Super-Resolution Quality Assessment
Authors:
Preprint
Abstract
There has emerged a growing interest in exploring efficient quality assessment algorithms for image super-resolution (SR). However, employing deep learning techniques, especially dual-branch algorithms, to automatically evaluate the visual quality of SR images remains challenging. Existing SR image quality assessment (IQA) metrics based on two-stream networks lack interactions between branches. To address this, we propose a novel full-reference IQA (FR-IQA) method for SR images. Specifically, producing SR images and evaluating how close the SR images are to the corresponding HR references are separate processes. Based on this consideration, we construct a deep Bi-directional Attention Network (BiAtten-Net) that dynamically deepens visual attention to distortions in both processes, which aligns well with the human visual system (HVS). Experiments on public SR quality databases demonstrate the superiority of our proposed BiAtten-Net over state-of-the-art quality assessment methods. In addition, the visualization results and ablation study show the effectiveness of bi-directional attention.Keywords
All Related Versions
This publication has 43 references indexed in Scilit:
- TADSRNet: A triple-attention dual-scale residual network for super-resolution image quality assessmentApplied Intelligence, 2023
- Super-resolution image visual quality assessment based on structure–texture featuresSignal Processing: Image Communication, 2023
- Self-attention negative feedback network for real-time image super-resolutionJournal of King Saud University Computer and Information Sciences, 2022
- Joint channel-spatial attention network for super-resolution image quality assessmentApplied Intelligence, 2022
- Blind quality assessment for image superresolution using deep two-stream convolutional networksInformation Sciences, 2020
- A reduced-reference quality assessment metric for super-resolution reconstructed images with information gain and texture similaritySignal Processing: Image Communication, 2019
- ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks2019
- Learning a no-reference quality metric for single-image super-resolutionComputer Vision and Image Understanding, 2017
- Image super-resolution as sparse representation of raw image patches2008
- New edge-directed interpolationIEEE Transactions on Image Processing, 2001