Self-Committee Approach for Image Restoration Problems using Convolutional Neural Network

05/12/2017
by   Byeongyong Ahn, et al.
0

There have been many discriminative learning methods using convolutional neural networks (CNN) for several image restoration problems, which learn the mapping function from a degraded input to the clean output. In this letter, we propose a self-committee method that can find enhanced restoration results from the multiple trial of a trained CNN with different but related inputs. Specifically, it is noted that the CNN sometimes finds different mapping functions when the input is transformed by a reversible transform and thus produces different but related outputs with the original. Hence averaging the outputs for several different transformed inputs can enhance the results as evidenced by the network committee methods. Unlike the conventional committee approaches that require several networks, the proposed method needs only a single network. Experimental results show that adding an additional transform as a committee always brings additional gain on image denoising and single image supre-resolution problems.

READ FULL TEXT

page 3

page 4

research
12/23/2018

Estimation and Restoration of Compositional Degradation Using Convolutional Neural Networks

Image restoration from a single image degradation type, such as blurring...
research
10/30/2021

Functional Neural Networks for Parametric Image Restoration Problems

Almost every single image restoration problem has a closely related para...
research
12/20/2016

Deeply Aggregated Alternating Minimization for Image Restoration

Regularization-based image restoration has remained an active research t...
research
07/03/2022

Variational Deep Image Restoration

This paper presents a new variational inference framework for image rest...
research
07/10/2019

Joint Learning of Multiple Image Restoration Tasks

Convolutional neural networks have recently been successfully applied to...
research
02/28/2019

Deep Inverse Tone Mapping Using LDR Based Learning for Estimating HDR Images with Absolute Luminance

In this paper, a novel inverse tone mapping method using a convolutional...
research
04/23/2019

Path-Restore: Learning Network Path Selection for Image Restoration

Very deep Convolutional Neural Networks (CNNs) have greatly improved the...

Please sign up or login with your details

Forgot password? Click here to reset