Learning a Mixture of Deep Networks for Single Image Super-Resolution

by   Ding Liu, et al.

Single image super-resolution (SR) is an ill-posed problem which aims to recover high-resolution (HR) images from their low-resolution (LR) observations. The crux of this problem lies in learning the complex mapping between low-resolution patches and the corresponding high-resolution patches. Prior arts have used either a mixture of simple regression models or a single non-linear neural network for this propose. This paper proposes the method of learning a mixture of SR inference modules in a unified framework to tackle this problem. Specifically, a number of SR inference modules specialized in different image local patterns are first independently applied on the LR image to obtain various HR estimates, and the resultant HR estimates are adaptively aggregated to form the final HR image. By selecting neural networks as the SR inference module, the whole procedure can be incorporated into a unified network and be optimized jointly. Extensive experiments are conducted to investigate the relation between restoration performance and different network architectures. Compared with other current image SR approaches, our proposed method achieves state-of-the-arts restoration results on a wide range of images consistently while allowing more flexible design choices. The source codes are available in http://www.ifp.illinois.edu/ dingliu2/accv2016.


page 8

page 9


Mapping Low-Resolution Images To Multiple High-Resolution Images Using Non-Adversarial Mapping

Several methods have recently been proposed for the Single Image Super-R...

Patch-based image Super Resolution using generalized Gaussian mixture model

Single Image Super Resolution (SISR) methods aim to recover the clean im...

Deep Constrained Least Squares for Blind Image Super-Resolution

In this paper, we tackle the problem of blind image super-resolution(SR)...

Raising The Limit Of Image Rescaling Using Auxiliary Encoding

Normalizing flow models using invertible neural networks (INN) have been...

D2C-SR: A Divergence to Convergence Approach for Image Super-Resolution

In this paper, we present D2C-SR, a novel framework for the task of imag...

Enhancing Image Rescaling using Dual Latent Variables in Invertible Neural Network

Normalizing flow models have been used successfully for generative image...

Towards Lightweight Super-Resolution with Dual Regression Learning

Deep neural networks have exhibited remarkable performance in image supe...

Please sign up or login with your details

Forgot password? Click here to reset