Reflection Removal for Images and 3D Point Clouds


Jacobs Hall, Room 2512, Jacobs School of Engineering, 9500 Gilman Dr, La Jolla, San Diego, California 92093

Sponsored By:
Truong Nguyen

Jae-Young Sim
Ulsan National institute of Science and Technology
Jae-Young Sim


We often capture images of a target scene through glass. For example, we take photographs of the products displayed in the show window, or take photographs of buildings with glass curtain walls. The captured glass image includes the target scene behind the glass as well as 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. In this seminar, we first talk about an automatic reflection removal algorithm for multiple glass images taken at slightly different camera locations. Also, with the advent of high-performance LiDAR scanners, large-scale 3D point clouds (LS3DPCs) for real-world scenes are being used in challenging applications. However, LS3DPCs captured by terrestrial LiDAR scanners also suffer from the reflection artifacts since many outdoor real-world structures include glasses. As a next topic, we define a problem of reflection in LS3DPCs and introduce our current research work on reflection removal for LS3DPCs.

Speaker Bio:
Jae-Young Sim received the B.S. degree in electrical engineering and the M.S. and Ph.D. degrees in electrical engineering and computer science from Seoul National University, Seoul, South Korea, in 1999, 2001, and 2005, respectively. From 2005 to 2009, he was a Research Staff Member with the Samsung Advanced Institute of Technology, Samsung Electronics Company, Ltd. In 2009, he joined the School of Electrical and Computer Engineering, Ulsan National Institute of Science and Technology, Ulsan, South Korea, where he is now an Associate Professor. His research interests include image, video, and 3D visual processing, computer vision, and multimedia data compression.

Travis Spackman (