Single Image Super Resolution - When Model Adaptation Matters

03/31/2017
by   Yudong Liang, et al.
0

In the recent years impressive advances were made for single image super-resolution. Deep learning is behind a big part of this success. Deep(er) architecture design and external priors modeling are the key ingredients. The internal contents of the low resolution input image is neglected with deep modeling despite the earlier works showing the power of using such internal priors. In this paper we propose a novel deep convolutional neural network carefully designed for robustness and efficiency at both learning and testing. Moreover, we propose a couple of model adaptation strategies to the internal contents of the low resolution input image and analyze their strong points and weaknesses. By trading runtime and using internal priors we achieve 0.1 up to 0.3dB PSNR improvements over best reported results on standard datasets. Our adaptation especially favors images with repetitive structures or under large resolutions. Moreover, it can be combined with other simple techniques, such as back-projection or enhanced prediction, for further improvements.

READ FULL TEXT

page 1

page 8

research
02/08/2018

Deep Image Super Resolution via Natural Image Priors

Single image super-resolution (SR) via deep learning has recently gained...
research
09/07/2019

Non-discriminative data or weak model? On the relative importance of data and model resolution

We explore the question of how the resolution of the input image ("input...
research
02/27/2020

Meta-Transfer Learning for Zero-Shot Super-Resolution

Convolutional neural networks (CNNs) have shown dramatic improvements in...
research
12/14/2018

Advanced Super-Resolution using Lossless Pooling Convolutional Networks

In this paper, we present a novel deep learning-based approach for still...
research
08/11/2020

Transfer Learning for Protein Structure Classification at Low Resolution

Structure determination is key to understanding protein function at a mo...
research
02/04/2021

Image Restoration by Deep Projected GSURE

Ill-posed inverse problems appear in many image processing applications,...
research
12/14/2021

Mitigating Channel-wise Noise for Single Image Super Resolution

In practice, images can contain different amounts of noise for different...

Please sign up or login with your details

Forgot password? Click here to reset