Inyoung Oh

Geometric Deep Learning · 3D Perception and Representation Learning · Mixed Reality and Spatial Computing

Hi, I’m Inyoung Oh, a Postdoctoral Fellow in the Visual Intelligence Group, Center for Artificial Intelligence, AI & Robotics Institute at the Korea Institute of Science and Technology (KIST). I received my Ph.D. in Mechanical and Robotics Engineering from Gwangju Institute of Science and Technology (GIST), advised by Prof. Kwanghee Ko in the MODSIM Lab.

My research focuses on geometric deep learning for robust 3D perception and spatial intelligence. I develop geometry-aware learning frameworks that explicitly incorporate geometric structure—such as surface normals, curvatures, discontinuities, and spatial relationships—into neural networks, enabling reliable representation learning under sparse, noisy, and real-world sensing conditions.

My work spans sharp feature detection, surface normal estimation, normal-guided LiDAR semantic segmentation, and monocular 6DoF pose estimation, with applications in robotics, autonomous systems, and mixed reality. These systems are designed to remain stable under real-world variability and to support deployable perception in practical environments.

At KIST, I am expanding this research toward RGB-driven 3D perception and monocular spatial understanding, focusing on estimating metric attributes such as 3D position and human height from monocular RGB input, enabling physically grounded spatial understanding. My goal is to advance spatial AI systems that achieve robust, physically grounded scene understanding across sensing modalities and real-world conditions.

Ultimately, I aim to develop representation learning frameworks where geometric structure serves as a fundamental inductive bias, enabling scalable and deployable perception for intelligent systems operating in complex physical environments.

Education

Ph.D. Candidate (2018–Present)
Gwangju Institute of Science and Technology (GIST), Gwangju, Republic of Korea
  • Major: Mechanical and Robotics Engineering
  • Advisor: Prof. Kwanghee Ko
  • GPA: 4.2 / 4.5
  • Expected Graduation: February 2026
  • Thesis: “Normal Vector Estimation, and Semantic Segmentation of 3D Point Clouds using Deep Learning and Geometric Analysis”
M.S. (2016–2018)
Gwangju Institute of Science and Technology (GIST), Gwangju, Republic of Korea
  • Major: Mechatronics
  • Advisor: Prof. Kwanghee Ko
  • GPA: 3.91 / 4.5
  • Thesis: “Sphere and Cylinder Detection in Kinect Point Clouds using the RANSAC and the 2D Hough Transform”
B.S. (2009–2016)
Chungnam National University, Daejeon, Republic of Korea
  • Major: Mechatronics Engineering
  • Advisor: Prof. Myounggyu Noh
  • GPA: 3.913 / 4.5
  • Thesis: “Research on Semi-Automatic Drills” (Grand Prize, Capstone Design Fair)

Teaching Experience

  • 2020 — Teaching Assistant, Engineering Analysis
    Led weekly recitations and office hours, developed exam content, and conducted biweekly Python sessions to boost students’ problem-solving skills.
  • 2017 — Teaching Assistant, Engineering Analysis
    Facilitated weekly recitations and office hours, crafted exam questions, and led biweekly MATLAB/C++ sessions to strengthen computational skills.
  • 2018–Present — Mentorship Experience, Modeling and Simulation Lab
    Provided one-on-one guidance over a year, overseeing data collection, lab organization, and problem-solving development that contributed to a bachelor’s thesis.

Awards

Awards
  • Best Poster Award, Korean CDE Society (2025)
  • Best Poster Award, Korean CDE Society (2024) — webzine
  • Best Poster Award, Korean CDE Society (2023)
  • CDE DX Encouragement Award, Korean CDE Society (2022)
  • Best Poster Award, Korean CDE Society (2021)
  • Best Poster Award, Korean CDE Society (2020)
Scholarship
  • Outstanding PhD Student RA Scholarship, GIST — 2018, 2019, 2020, 2021, 2023, 2025
  • GIST Scholarship (Government support – Doctoral studies) — 2018–Present
  • GIST Scholarship (Government support – Master’s studies) — 2016–2018