VIP Lab’s paper accepted to IEEE Transactions on Image Processing

Activities June 26, 2018


UNIST ECE student, Byeong-Ju Han and Prof. Jae-Young Sim’s paper has been accepted to IEEE Transactions on Image Processing, the most prestigious journal in the field of image processing.

The images taken through glass usually include a target scene behind the glass as well as an undesired reflected scene in front of the glass, since light passes through and is reflected on a pane of glass simultaneously. Such reflection artifacts may degrade the performance of image processing and computer vision techniques when applied to glass images. The authors propose a novel reflection removal algorithm using multiple glass images taken from slightly different camera positions.


For more information, please refer to the publication details:

Authors: Byeong-Ju Han and Jae-Young Sim (corresponding author)

Title: Glass reflection removal using co-saliency based image alignment and low-rank matrix completion in gradient domain

Journal: IEEE Transactions on Image Processing (IF: 4.828)