Blind Super-Resolution Kernel Estimation using an Internal-GAN

09/14/2019
by   Sefi Bell-Kligler, et al.
4

Super resolution (SR) methods typically assume that the low-resolution (LR) image was downscaled from the unknown high-resolution (HR) image by a fixed 'ideal' downscaling kernel (e.g. Bicubic downscaling). However, this is rarely the case in real LR images, in contrast to synthetically generated SR datasets. When the assumed downscaling kernel deviates from the true one, the performance of SR methods significantly deteriorates. This gave rise to Blind-SR - namely, SR when the downscaling kernel ("SR-kernel") is unknown. It was further shown that the true SR-kernel is the one that maximizes the recurrence of patches across scales of the LR image. In this paper we show how this powerful cross-scale recurrence property can be realized using Deep Internal Learning. We introduce "KernelGAN", an image-specific Internal-GAN, which trains solely on the LR test image at test time, and learns its internal distribution of patches. Its Generator is trained to produce a downscaled version of the LR test image, such that its Discriminator cannot distinguish between the patch distribution of the downscaled image, and the patch distribution of the original LR image. The Generator, once trained, constitutes the downscaling operation with the correct image-specific SR-kernel. KernelGAN is fully unsupervised, requires no training data other than the input image itself, and leads to state-of-the-art results in Blind-SR when plugged into existing SR algorithms.

READ FULL TEXT

page 2

page 7

page 8

research
12/17/2017

"Zero-Shot" Super-Resolution using Deep Internal Learning

Deep Learning has led to a dramatic leap in Super-Resolution (SR) perfor...
research
12/15/2022

Meta-Learned Kernel For Blind Super-Resolution Kernel Estimation

Recent image degradation estimation methods have enabled single-image su...
research
01/09/2020

Fast Adaptation to Super-Resolution Networks via Meta-Learning

Conventional supervised super-resolution (SR) approaches are trained wit...
research
12/01/2018

Internal Distribution Matching for Natural Image Retargeting

Good Visual Retargeting changes the global size and aspect ratio of a na...
research
12/19/2021

A-ESRGAN: Training Real-World Blind Super-Resolution with Attention U-Net Discriminators

Blind image super-resolution(SR) is a long-standing task in CV that aims...
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
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