Notice

UNIST ECE student, Jae-Seong Yun and Prof. Jae-Young Sim’s paper has been accepted to CVPR 2018.

 

Authors: Jae-Seong Yun and Jae-Young Sim (corresponding author)

Title: Reflection Removal for Large-Scale 3D Point Clouds

Conference: 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

 

With the advent of LiDAR scanners, large-scale 3D point clouds (LS3DPCs) have been attracting interests and their applications are expanding nowadays. LS3DPCs suffer from reflection artifacts since many outdoor real-world structures include glasses. In this work, we first defined a problem of reflection removal for LS3DPCs and devised an efficient algorithm to solve this problem. This research is a pioneering work to improve the geometric accuracy of LS3DPCs and thus can be a core technology for various applications such as realistic VR/MR content generation and autonomous vehicles.

 

CVPR is an annual conference on computer vision and pattern recognition published by IEEE. CVPR is regarded as the most prestige conference in computer vision and also ranked 35th among all publications in Google Scholar.