Deep learning architectural designs for super-resolution of noisy images

by   Angel Villar-Corrales, et al.

Recent advances in deep learning have led to significant improvements in single image super-resolution (SR) research. However, due to the amplification of noise during the upsampling steps, state-of-the-art methods often fail at reconstructing high-resolution images from noisy versions of their low-resolution counterparts. However, this is especially important for images from unknown cameras with unseen types of image degradation. In this work, we propose to jointly perform denoising and super-resolution. To this end, we investigate two architectural designs: "in-network" combines both tasks at feature level, while "pre-network" first performs denoising and then super-resolution. Our experiments show that both variants have specific advantages: The in-network design obtains the strongest results when the type of image corruption is aligned in the training and testing dataset, for any choice of denoiser. The pre-network design exhibits superior performance on unseen types of image corruption, which is a pathological failure case of existing super-resolution models. We hope that these findings help to enable super-resolution also in less constrained scenarios where source camera or imaging conditions are not well controlled. Source code and pretrained models are available at angelvillar96/super-resolution-noisy-images.


page 3

page 4


Blind Image Super-Resolution with Spatial Context Hallucination

Deep convolution neural networks (CNNs) play a critical role in single i...

Feedback Network for Image Super-Resolution

Recent advances in image super-resolution (SR) explored the power of dee...

Rethinking Degradation: Radiograph Super-Resolution via AID-SRGAN

In this paper, we present a medical AttentIon Denoising Super Resolution...

Bayesian Image Reconstruction using Deep Generative Models

Machine learning models are commonly trained end-to-end and in a supervi...

StofNet: Super-resolution Time of Flight Network

Time of Flight (ToF) is a prevalent depth sensing technology in the fiel...

Decouple Learning for Parameterized Image Operators

Many different deep networks have been used to approximate, accelerate o...

Super-Resolution of License Plate Images Using Attention Modules and Sub-Pixel Convolution Layers

Recent years have seen significant developments in the field of License ...

Please sign up or login with your details

Forgot password? Click here to reset