Image Super-Resolution via Deterministic-Stochastic Synthesis and Local Statistical Rectification

09/18/2018
by   Weifeng Ge, et al.
12

Single image superresolution has been a popular research topic in the last two decades and has recently received a new wave of interest due to deep neural networks. In this paper, we approach this problem from a different perspective. With respect to a downsampled low resolution image, we model a high resolution image as a combination of two components, a deterministic component and a stochastic component. The deterministic component can be recovered from the low-frequency signals in the downsampled image. The stochastic component, on the other hand, contains the signals that have little correlation with the low resolution image. We adopt two complementary methods for generating these two components. While generative adversarial networks are used for the stochastic component, deterministic component reconstruction is formulated as a regression problem solved using deep neural networks. Since the deterministic component exhibits clearer local orientations, we design novel loss functions tailored for such properties for training the deep regression network. These two methods are first applied to the entire input image to produce two distinct high-resolution images. Afterwards, these two images are fused together using another deep neural network that also performs local statistical rectification, which tries to make the local statistics of the fused image match the same local statistics of the groundtruth image. Quantitative results and a user study indicate that the proposed method outperforms existing state-of-the-art algorithms with a clear margin.

READ FULL TEXT

page 1

page 2

page 6

page 7

page 9

page 10

page 14

research
07/07/2016

Deep Depth Super-Resolution : Learning Depth Super-Resolution using Deep Convolutional Neural Network

Depth image super-resolution is an extremely challenging task due to the...
research
09/03/2018

Unsupervised Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networks

We consider the single image super-resolution problem in a more general ...
research
05/24/2018

Deep Residual Networks with a Fully Connected Recon-struction Layer for Single Image Super-Resolution

Recently, deep neural networks have achieved impressive performance in t...
research
03/01/2019

Deep Learning for Multiple-Image Super-Resolution

Super-resolution reconstruction (SRR) is a process aimed at enhancing sp...
research
07/25/2016

Local- and Holistic- Structure Preserving Image Super Resolution via Deep Joint Component Learning

Recently, machine learning based single image super resolution (SR) appr...
research
07/16/2022

Stochastic Attribute Modeling for Face Super-Resolution

When a high-resolution (HR) image is degraded into a low-resolution (LR)...
research
05/13/2022

FontNet: Closing the gap to font designer performance in font synthesis

Font synthesis has been a very active topic in recent years because manu...

Please sign up or login with your details

Forgot password? Click here to reset