Accurate and Lightweight Image Super-Resolution with Model-Guided Deep Unfolding Network

09/14/2020
by   Qian Ning, et al.
9

Deep neural networks (DNNs) based methods have achieved great success in single image super-resolution (SISR). However, existing state-of-the-art SISR techniques are designed like black boxes lacking transparency and interpretability. Moreover, the improvement in visual quality is often at the price of increased model complexity due to black-box design. In this paper, we present and advocate an explainable approach toward SISR named model-guided deep unfolding network (MoG-DUN). Targeting at breaking the coherence barrier, we opt to work with a well-established image prior named nonlocal auto-regressive model and use it to guide our DNN design. By integrating deep denoising and nonlocal regularization as trainable modules within a deep learning framework, we can unfold the iterative process of model-based SISR into a multi-stage concatenation of building blocks with three interconnected modules (denoising, nonlocal-AR, and reconstruction). The design of all three modules leverages the latest advances including dense/skip connections as well as fast nonlocal implementation. In addition to explainability, MoG-DUN is accurate (producing fewer aliasing artifacts), computationally efficient (with reduced model parameters), and versatile (capable of handling multiple degradations). The superiority of the proposed MoG-DUN method to existing state-of-the-art image SR methods including RCAN, SRMDNF, and SRFBN is substantiated by extensive experiments on several popular datasets and various degradation scenarios.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 5

page 6

page 7

page 10

page 11

03/23/2018

Fast, Accurate, and, Lightweight Super-Resolution with Cascading Residual Network

In recent years, deep learning methods have been successfully applied to...
05/21/2021

Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile Devices

Single-Image Super Resolution (SISR) is a classical computer vision prob...
07/07/2019

FC^2N: Fully Channel-Concatenated Network for Single Image Super-Resolution

Most current image super-resolution (SR) methods based on deep convoluti...
01/21/2018

Denoising Prior Driven Deep Neural Network for Image Restoration

Deep neural networks (DNNs) have shown very promising results for variou...
03/23/2020

Deep Unfolding Network for Image Super-Resolution

Learning-based single image super-resolution (SISR) methods are continuo...
04/28/2022

Deep Generalized Unfolding Networks for Image Restoration

Deep neural networks (DNN) have achieved great success in image restorat...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.