Hee Jae Kim

I am a second-year Ph.D. student at Boston University, advised by Prof. Eshed Ohn-Bar. My research interests lie in computer vision, robotics, and machine learning with their applications in autonomous and assistive systems.

Prior to BU, I got my master's degree (2019-2021) at the Ewha Womans University, where I worked with Prof. Byung-Uk Lee and Prof. Jewon Kang, on multi-view 360-degree videos.

In 2018, I worked as a research intern at the Artificial Intelligence Research Center at ETRI (Korea). In 2021, I worked as a researcher at RainbirdGEO.

Email  /  Scholar  /  Github  /  CV

Research

We introduce Motion Diversification Networks, a novel framework for learning to generate realistic and diverse 3D human motion. Towards more realistic and functional 3D motion models, this work uncovers limitations in existing generative modeling techniques, particularly in overly simplistic latent code sampling strategies.

This study aims to explore the cloud properties of tropical convective clouds (TCC) that indicate a high probability of precipitation by training a neural network with daytime satellite imagery.

We propose an efficient reference-based 360° image super-resolution (RefSR) technique to exploit a wide field of view (FoV) among adjacent 360° cameras. We do not assume any structured camera arrays but use a reference image captured in an arbitrary viewpoint. Accordingly, we develop a long-range 360 disparity estimator (DE360) to overcome a large and distorted disparity between equirectangular projection (ERP) images, particularly near the poles.