Jinbum Park

M.S. student in the Deep Image Processing Lab at Korea University.

209, Nonhyeon, Gangnam-gu, Seoul, Republic of Korea 06270

I am a graduate student in the Deep Image Processing Lab, advised by Prof. Seung-Won Jung. Currently pursuing the MS degree in Electrical Engineering at Korea University in Seoul, Korea. Previously, I worked at LG Electronics for 4 years as a Computer/Machine Vision engineer. I received my B.S. in Electronic Engineering at University of California San Diego. My research interests are including :

Computer/Machine Vision
Deep Learning(Image enhancement, object detection)
Camera ISP

You will find my resume attached below. Resume

Experience

Aug, 2018 - Feb, 2022	LG Electronics, Republic of Korea Production engineering Research Institute PRI R&D

Education

Mar, 2022 - Present	Korea University, Seoul, South Korea Master Degree Student in Electrical Engineering Advisor: Prof. Seung-Won Jung.
Sep, 2013 - May, 2018	University of California, San Diego, San Diego CA ,United States of America B.S in Electronic Engineering

Selected Publications

Monocular Depth Estimation Network with Single-Pixel Depth Guidance

Lee, Hongjae, Park, Jinbum, Jeong, Wooseok, and Jung, Seung-Won

Optics Letters 2022

Abs Code

Due to the scale ambiguity problem, the performance of monocular depth estimation (MDE) is inherently restricted. Multi-camera systems, especially those equipped with active depth cameras, have addressed this problem at the expense of increased hardware costs and space. In this Letter, we adopt a similar but costeffective solution using only single-pixel depth guidance with a single-photon avalanche diode. To this end, we design a single-pixel guidance module (SPGM) that combines the global information from the single-pixel depth guidance with the spatial information from the image at the feature level. By integrating SPGMs into an MDE network, we introduce PhoMoNet, the first end-to-end MDE network with single-pixel depth guidance. Experimental results show the effectiveness and superiority of PhoMoNet over state-of-the-art MDE networks on synthetic and real-world datasets.