Unfolding the Alternating Optimization for Blind Super Resolution

10/06/2020
by   Zhengxiong Luo, et al.
5

Previous methods decompose blind super resolution (SR) problem into two sequential steps: i) estimating blur kernel from given low-resolution (LR) image and ii) restoring SR image based on estimated kernel. This two-step solution involves two independently trained models, which may not be well compatible with each other. Small estimation error of the first step could cause severe performance drop of the second one. While on the other hand, the first step can only utilize limited information from LR image, which makes it difficult to predict highly accurate blur kernel. Towards these issues, instead of considering these two steps separately, we adopt an alternating optimization algorithm, which can estimate blur kernel and restore SR image in a single model. Specifically, we design two convolutional neural modules, namely Restorer and Estimator. Restorer restores SR image based on predicted kernel, and Estimator estimates blur kernel with the help of restored SR image. We alternate these two modules repeatedly and unfold this process to form an end-to-end trainable network. In this way, Estimator utilizes information from both LR and SR images, which makes the estimation of blur kernel easier. More importantly, Restorer is trained with the kernel estimated by Estimator, instead of ground-truth kernel, thus Restorer could be more tolerant to the estimation error of Estimator. Extensive experiments on synthetic datasets and real-world images show that our model can largely outperform state-of-the-art methods and produce more visually favorable results at much higher speed. The source code is available at https://github.com/greatlog/DAN.git.

READ FULL TEXT

page 3

page 6

page 7

page 9

research
05/14/2021

End-to-end Alternating Optimization for Blind Super Resolution

Previous methods decompose the blind super-resolution (SR) problem into ...
research
04/06/2019

Blind Super-Resolution With Iterative Kernel Correction

Deep learning based methods have dominated super-resolution (SR) field d...
research
02/16/2023

Kernelized Back-Projection Networks for Blind Super Resolution

Since non-blind Super Resolution (SR) fails to super-resolve Low-Resolut...
research
03/11/2015

Simple, Accurate, and Robust Nonparametric Blind Super-Resolution

This paper proposes a simple, accurate, and robust approach to single im...
research
03/06/2020

Pixel-Level Self-Paced Learning for Super-Resolution

Recently, lots of deep networks are proposed to improve the quality of p...
research
07/31/2018

Learning Collaborative Generation Correction Modules for Blind Image Deblurring and Beyond

Blind image deblurring plays a very important role in many vision and mu...
research
05/20/2023

Dual-Diffusion: Dual Conditional Denoising Diffusion Probabilistic Models for Blind Super-Resolution Reconstruction in RSIs

Previous super-resolution reconstruction (SR) works are always designed ...

Please sign up or login with your details

Forgot password? Click here to reset