본 연구실 졸업생인 김한솔 박사가 연구한 “Self-learning based joint multi image super-resolution and sub-pixel registration” 제목의 논문이 Digital Signal Processing (Impact factor : 2.9, Rank : Q2)에 게재가 확정되었다. 본 연구는 김한솔 박사(1저자)와 동서대학교 정보통신공학과 이석호 교수(2저자), 강문기 교수(교신저자)가 진행하였다.

Abstract

Multi Image Super-resolution (MISR) refers to the task of enhancing the spatial resolution of a stack of lowresolution (LR) images representing the same scene. Although many deep learning-based single image superresolution (SISR) technologies have recently been developed, deep learning has not been widely exploited for

MISR, even though it can achieve higher reconstruction accuracy because more information can be extracted

from the stack of LR images. One of the primary obstacles encountered by deep networks when addressing the

MISR problem is the variability in the number of LR images that act as input to the network. This impedes the

feasibility of adopting an end-to-end learning approach, because the varying number of input images makes

it difficult to construct a training dataset for the network. Another challenge arises from the requirement to

align the LR input images to generate high-resolution (HR) image of high quality, which requires complex and

sophisticated methods.

In this paper, we propose a self-learning based method that can simultaneously perform super-resolution and

sub-pixel registration of multiple LR images. The proposed method trains a neural network with only the LR

images as input and without any true target HR images; i.e., the proposed method requires no extra training

dataset. Therefore, it is easy to use the proposed method to deal with different numbers of input images. To

our knowledge this is the first time that a neural network is trained using only LR images to perform a joint

MISR and sub-pixel registration. Experimental results confirmed that the HR images generated by the proposed

method achieved better results in both quantitative and qualitative evaluations than those generated by other

deep learning-based methods.