profile picture

Minhyuk Sung

Research Scientist
Adobe Research

About Me

I completed my Ph.D. in Computer Science department at Stanford University advised by Leonidas Guibas. My recent research focuses on deep-learning-based 3D shape analysis and synthesis for graphics/vision applications. Previously, I have interned at Google, Adobe Research, and Autodesk Research, and worked as a researcher at Korea Institute of Science and Technology (KIST). I received MS and BS degrees in Computer Science at Korea Advanced Institute of Science and Technology (KAIST).


Publications

thumbnail
Learning and exploring the compositional structure of 3D data
Minhyuk Sung
Ph.D. Thesis. Stanford University. 2019.
Link
thumbnail
Supervised Fitting of Geometric Primitives to 3D Point Clouds
Lingxiao Li*, Minhyuk Sung*, Anastasia Dubrovina, Li Yi, and Leonidas Guibas (* equal contribution)
CVPR 2019 (Oral)
arXiv | Code
thumbnail
GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud
Li Yi, Wang Zhao, He Wang, Minhyuk Sung, and Leonidas Guibas
CVPR 2019
arXiv
thumbnail
Deep Functional Dictionaries: Learning Consistent Semantic Structures on 3D Models from Functions
Minhyuk Sung, Hao Su, Ronald Yu, and Leonidas Guibas
NeurIPS 2018
arXiv | PDF | Poster | Code
thumbnail
Image Unprojection for 3D Surface Reconstruction: A Triangulation-based Approach
Minhyuk Sung, Hwasup Lim, Hyoung-Gon Kim, and Sang Chul Ahn
IEEE International Conference on Image Processing (ICIP) 2013
PDF
thumbnail
Finding the M-best consistent correspondences between 3D symmetric objects
Minhyuk Sung, and Junho Kim
Computers & Graphics. 2013.
Link
thumbnail
A Triangulation-Invariant Method for Anisotropic Geodesic Map Computation on Surface Meshes
Sang Wook Yoo, Joon-Kyung Seong, Min-Hyuk Sung, Sung Yong Shin and Elaine Cohen
IEEE Transactions on Visualization and Computer Graphics (TVCG). 2012
Link
thumbnail
A Spectral Approach to Shape Matching Using a Heat Kernel Function
Min-Hyuk Sung
M.S. Thesis. Korea Advanced Institute of Science and Technology (KAIST). 2010.
Link