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

by   Qian Ning, et al.

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.



There are no comments yet.


page 1

page 2

page 5

page 6

page 7

page 10

page 11


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

In recent years, deep learning methods have been successfully applied to...

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

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

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

Most current image super-resolution (SR) methods based on deep convoluti...

Denoising Prior Driven Deep Neural Network for Image Restoration

Deep neural networks (DNNs) have shown very promising results for variou...

Deep Unfolding Network for Image Super-Resolution

Learning-based single image super-resolution (SISR) methods are continuo...

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.