Minhyuk Sung

Assistant Professor
School of Computing
KAIST

About Me

I am an assistant professor in the School of Computing at KAIST (also affiliated with the Graduate School of AI). Before joining KAIST, I was a research scientist at Adobe Research. I received my Ph.D. from Stanford University, advised by Leonidas Guibas, and received M.S. and B.S. degrees from KAIST. My research focuses on 3D deep learning and geometry processing.

I am looking for new graduate students to join my group. Please reach out to me via email if you are interested in.

CV | Google Scholar | GitHub

Research Statement (Presented at SIGGRAPH 2019 Doctoral Consortium)

Publications

CPFN: Cascaded Primitive Fitting Networks for High-Resolution Point Clouds
Eric-Tuan Lê, Minhyuk Sung, Duygu Ceylan, Radomír Měch, Tamy Boubekeur, Niloy Mitra
ICCV 2021
arXiv | Code

CTRL-C: Camera calibration TRansformer with Line-Classification
Jinwoo Lee, Hyunsung Go, Hyunjoon Lee, Sunghyun Cho, Minhyuk Sung, Junho Kim
ICCV 2021
arXiv | Code

DeepMetaHandles: Learning Deformation Meta-Handles of 3D Meshes with Biharmonic Coordinates
Minghua Liu, Minhyuk Sung, Radomír Měch, Hao Su
CVPR 2021 (Oral)
Project | arXiv | Code | Web Demo | Supplementary (Animations)

MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization
Jiahui Huang, He Wang, Tolga Birdal, Minhyuk Sung, Federica Arrigoni, Shi-Min Hu, Leonidas Guibas
CVPR 2021 (Oral)
Project | arXiv | Code

Joint Learning of 3D Shape Retrieval and Deformation
Mikaela Angelina Uy, Vladimir G. Kim, Minhyuk Sung, Noam Aigerman, Siddhartha Chaudhuri, Leonidas Guibas
CVPR 2021
Project | arXiv | Code

DeformSyncNet: Deformation Transfer via Synchronized Shape Deformation Spaces
Minhyuk Sung*, Zhenyu Jiang*, Panos Achlioptas, Niloy Mitra, Leonidas Guibas (* equal contribution)
SIGGRAPH Asia 2020
Project | arXiv | PDF | Code

Deformation-Aware 3D Shape Embedding and Retrieval
Mikaela Angelina Uy, Jingwei Huang, Minhyuk Sung, Tolga Birdal, Leonidas Guibas
ECCV 2020
Project | arXiv | Slides | Code

Neural Geometric Parser for Single Image Camera Calibration
Jinwoo Lee, Minhyuk Sung, Hyunjoon Lee, Junho Kim
ECCV 2020
arXiv

Pix2Surf: Learning Parametric 3D Surface Models of Objects from Images
Jiahui Lei, Srinath Sridhar, Paul Guerrero, Minhyuk Sung, Niloy Mitra, Leonidas Guibas
ECCV 2020
Project | arXiv | PDF | Supplementary | Code

Learning 3D Part Assembly from a Single Image
Yichen Li*, Kaichun Mo*, Lin Shao, Minhyuk Sung, Leonidas Guibas (* equal contribution)
ECCV 2020
Project | arXiv | Slides | Code

Learning and Exploring the Compositional Structure of 3D Data
Minhyuk Sung
Dissertation. Stanford University. 2019.
Link

Supervised Fitting of Geometric Primitives to 3D Point Clouds
Lingxiao Li*, Minhyuk Sung*, Anastasia Dubrovina, Li Yi, Leonidas Guibas (* equal contribution)
CVPR 2019 (Oral)
arXiv | Video | Code

GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud
Li Yi, Wang Zhao, He Wang, Minhyuk Sung, Leonidas Guibas
CVPR 2019
arXiv | Code

Deep Functional Dictionaries: Learning Consistent Semantic Structures on 3D Models from Functions
Minhyuk Sung, Hao Su, Ronald Yu, Leonidas Guibas
NeurIPS 2018
arXiv | PDF | Poster | Code

Learning Fuzzy Set Representations of Partial Shapes on Dual Embedding Spaces
Minhyuk Sung, Anastasia Dubrovina, Vladimir G. Kim, Leonidas Guibas
SGP 2018 (Symposium on Geometry Processing)
Project | arXiv | PDF | Slides (PPTX) | Code

ComplementMe: Weakly-Supervised Component Suggestions for 3D Modeling
Featured in an ACM press release: [link1] [link2]
Minhyuk Sung, Hao Su, Vladimir G. Kim, Siddhartha Chaudhuri, Leonidas Guibas
SIGGRAPH Asia 2017
Project | arXiv | PDF | Slides (PPTX) | Code

Data-Driven Structural Priors for Shape Completion
Minhyuk Sung, Vladimir G. Kim, Roland Angst, Leonidas Guibas
SIGGRAPH Asia 2015
Project | PDF | Supplementary | Slides (PPTX) | Code

Image Unprojection for 3D Surface Reconstruction: A Triangulation-based Approach
Min-Hyuk Sung, Hwasup Lim, Hyoung-Gon Kim, Sang Chul Ahn
IEEE International Conference on Image Processing (ICIP) 2013
Link

Finding the M-best consistent correspondences between 3D symmetric objects
Min-Hyuk Sung and Junho Kim
Computers & Graphics. 2013.
Link

A Triangulation-Invariant Method for Anisotropic Geodesic Map Computation on Surface Meshes
Sang Wook Yoo, Joon-Kyung Seong, Min-Hyuk Sung, Sung Yong Shin, Elaine Cohen
IEEE Transactions on Visualization and Computer Graphics (TVCG). 2012
Link

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

Courses

CS492(D): Geometric Modeling and Processing, Fall 2021.
CS492(H): Machine Learning for 3D Data, Spring 2021.