Minhyuk Sung

Assistant Professor
School of Computing
Graduate School of AI
KAIST

KAIST Visual AI Group

Contact Information

N1, Rm 607, KAIST
291 Daehak-ro, Yuseong-gu,
Daejeon, South Korea 34141
Tel: (+82)-042-350-3587

Courses

CS492(D): Diffusion Models and Their Applications
Fall 2024
CS580: Computer Graphics
Spring 2024
CS479: Machine Learning for 3D Data
Fall 2023

I am an assistant professor in the School of Computing at KAIST, leading the KAIST Visual AI Group. I am also affiliated with the Graduate School of AI and the Metaverse Program. 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 generating, analyzing, and manipulating visual data based on learning novel neural representations. I’m the recipient of the Asiapgraphics Researcher Award in 2024.

I am looking for motivated students to join my group. Please reach out to me via email if you are interested in.
Information for Prospective Students

Announcements

Call for Internship for Winter 2024: We are currently seeking undergraduate interns to join our group this winter. Click here for more details.

News

Sep 2024

Four papers have been accepted to NeurIPS 2024.

Sep 2024

I won the Asiagraphics Young Researcher Award in 2024!

Sep 2024

Serving as an area chair at ICLR 2024.

Aug 2024

I presented a tutorial on "Diffusion Models for Visual Content Generation" at SIGGRAPH 2024. Click here for more details.

Jul 2024

I gave talks at Stanford and Adobe Research on "Visual Content Generation with Image Diffusion Models". Click here to download the slides.

Jul 2024

Two papers have been accepted to ECCV 2024.

Jun 2024

I presented at the 2nd Workshop on Compositional 3D Vision (C3DV) at CVPR 2024. Click here to download the slides.

Jun 2024

Serving as an International Program Committee member at Eurographics 2025.

Apr 2024

I gave talks at TUM, ETH, and École Polytechnique on "Visual Content Generation with Image Diffusion Models". Click here to download the slides.

Mar 2024

Serving as a technical paper committee member at SIGGRAPH Asia 2024.

Apr 2024

I presented a tutorial on "Diffusion Models for Visual Computing" at Eurographics 2024. Click here for more details.

Mar 2024

Serving as a technical paper committee member at SIGGRAPH Asia 2024.

Feb 2024

Three papers have been accepted at CVPR 2024.

Jan 2024

I gave a talk at POSTECH.

Dec 2023

I gave a talk at NVIDIA Toronto AI Lab with the title: "Moving Beyond 3D Generation to Editing with Image Diffusion Priors". Click here to download the slides.

Oct 2023

One paper accepted to 3DV 2024.

Oct 2023

I presented a tutorial at Pacific Graphics 2023 about 3D generative models. Click here for more details.

Oct 2023

I gave a talk at University College London and Adobe Research Paris with the title: "Towards Shape Editability and Multi-View Consistency in 3D Generation". Click here to download the slides.

Sep 2023

Two papers accepted to NeurIPS 2023. Congratulations Yuseung on the first paper! Please check out our Hugging Face demo on our project webpage by clicking here.

Sep 2023

I gave a talk as a colloquium speaker at the KAIST Metaverse Program.

Aug 2023

OptCtrlPoints has been accepted to Pacific Graphics 2023 as a full paper. Congrats Kunho!

Aug 2023

Serving as an International Program Committee member at Eurographics 2024.

Jul 2023

SALAD has been accepted at ICCV 2023. Kudos to Juil, Seungwoo, and Hieu! Click here to check out our Hugging Face demo on our project webpage.

Jul 2023

I gave a talk at Samsung Advanced Institute of Technology.

Jul 2023

I presented a tutorial talk at the Korea AI Association conference titled "3D Generation via 2D Priors and Neural Rendering: Recent Advances, Limitations, and Future Directions." Click here to download the slides.

Jul 2023

I gave a talk at Ontact Health.

Jun 2023

I gave a talk at Osstem Implant.

Jun 2023

I gave a talk about 3D generative models at the POSTECH CSE/GSAI seminar series. Click to download the slides.

Apr 2023

Serving as a technical paper committee member at SIGGRAPH Asia 2023.

Apr 2023

Serving as a program committee member and a local arrangement chair at Pacific Graphics 2023.

Mar 2023

Co-organizing a workshop at CVPR 2023: Structural and Compositional Learning on 3D Data.

Feb 2023

Two papers accepted to CVPR 2023.

Jan 2023

I uploaded the lecture recordings of the 3D ML course on the course webpage. Click this to move to the course webpage. Hope the lectures would be helpful to students studying 3D ML.

Dec 2022

Juil Koo passed his M.S. thesis defense. Congrats!

Nov 2022

Hosted KAIST Geometric and Visual Computing Workshop (GVC Workshop). Click this for more details.

Nov 2022

I gave a talk about language and 3D & differential Poisson Solver at the KAIST GSAI Colloquium and KIST. Click to download the slides.

Oct 2022

We are now looking for undergraduate interns to join our group this winter. Click for more details. The deadline is Nov 14 (Mon), 23:59 KST.

Oct 2022

One paper accepted to WACV 2023 (Algorithm Track).

Oct 2022

One paper accepted to Findings of EMNLP 2022.

Sep 2022

We are now recruiting master's students to join our group next spring. Click this to apply. The deadline is Oct 7 (Fri), 23:59 KST.

Sep 2022

Serving as a senior program committee member at AAAI 2023.

Aug 2022

We are hosting the 2022 Women Tech Stars workshop at KAIST, supported by the Google ExploreCSR program. Click this to check out the webpage.

Aug 2022

Visited GrUVi at SFU on the trip to SIGGRAPH 2022 and gave a talk.

Aug 2022

Serving as an associate editor of Graphical Models.

Aug 2022

I wrote a blog post about 'How do I structure a paper?' at SIGGRAPH Research Career Development Committee (RCDC) webpage. Click to check it out.

Jul 2022

Presented a keynote talk at the ICME Workshop on 3D Multimedia Analytics, Search and Generation.

Jul 2022

Virtually visited Mohamed Elhoseiny's group at KAUST and gave a talk about language and 3D.

Jul 2022

I gave a lecture on "Introduction to Neural Rendering" at the Summer School of KCGS 2022. Click to download the slides.

Jul 2022

One paper accepted to ECCV 2022.

Jun 2022

I gave a talk at KCC 2022.

Jun 2022

Visited Stanford University and gave a talk about language and 3D. Click to download the slides.

May 2022

We are now looking for undergraduate interns to join our group this summer. Click this for more details.

Apr 2022

I gave a talk at Samsung Display about neural rendering.

Apr 2022

Serving as a technical paper committee member at SIGGRAPH Asia 2022.

Mar 2021

Three papers accepted to CVPR 2022 including Juil's oral.

Mar 2022

I gave a talk at the First Wednesday Multidisciplinary Forum at KAIST.

Feb 2022

Invited as a webinar speaker at Asiagraphics.

Feb 2022

One paper accepted to ICRA 2022.

Oct 2021

I gave a talk at the Manufacturing Technology Center at Samsung Electronics.

Oct 2021

I gave a talk as a colloquium speaker in the School of Biomedical Engineering at Korea University.

Sep 2021

Serving as an International Program Committee member at Eurographics 2022.

Sep 2021

I gave a talk as a seminar speaker in the School of Integrated Technology at GIST.

Sep 2021

We have been awarded the Google exploreCSR grant for the Rising Stars 2022 program at KAIST. Stay tuned for the details of the event!

Jul 2021

Two papers accepted to ICCV 2021.

Jul 2021

I gave a talk at the Korea Computer Graphics Society 2021.

May 2021

I gave a talk as a colloquium speaker in the School of Computing at KAIST.

Apr 2021

Co-organizing a workshop at ICCV 2021: Structural and Compositional Learning on 3D Data.

Apr 2021

I gave a talk as a colloquium speaker in the Software Graduate Program at KAIST.

Mar 2021

Three papers accepted to CVPR 2021 including two orals.

Feb 2021

I gave a talk at the Computer Vision Researcher Forum of Korean Computer Vision Society

Feb 2021

I gave a talk at the Graduate School of Culture Technology at KAIST.

Jan 2021

I gave a talk at Kakao Brain.

Jan 2021

I started as an assistant professor in the School of Computing at KAIST.

Less

Publications

SyncTweedies: A General Generative Framework Based on Synchronized Diffusions

Jaihoon Kim*, Juil Koo*, Kyeongmin Yeo*, Minhyuk Sung (* equal contributions)
NeurIPS 2024
Project arXiv PDF Code

Neural Pose Representation Learning for Generating and Transferring Non-Rigid Object Poses

Seungwoo Yoo, Juil Koo, Kyeongmin Yeo, Minhyuk Sung
NeurIPS 2024
arXiv

GrounDiT: Grounding Diffusion Transformers via Noisy Patch Transplantation

Phillip Y. Lee*, Taehoon Yoon*, Minhyuk Sung (* equal contributions)
NeurIPS 2024
Project arXiv

MV2Cyl: Reconstructing 3D Extrusion Cylinders from Multi-View Images

Eunji Hong, Nguyen Minh Hieu, Mikaela Angelina Uy, Minhyuk Sung
NeurIPS 2024
arXiv

Occupancy-Based Dual Contouring

Jisung Hwang, Minhyuk Sung
SIGGRAPH Asia 2024
arXiv Code

ReGround: Improving Textual and Spatial Grounding at No Cost

Phillip Y. Lee, Minhyuk Sung
ECCV 2024
Project arXiv PDF

PartSTAD: 2D-to-3D Part Segmentation Task Adaptation

Hyunjin Kim, Minhyuk Sung
ECCV 2024
arXiv Code

Posterior Distillation Sampling

Juil Koo, Chanho Park, Minhyuk Sung
CVPR 2024
Project arXiv PDF Code Hugging Face

As-Plausible-As-Possible: Semantic-Aware Shape Deformation using 2D Diffusion Priors

Seungwoo Yoo*, Kunho Kim*, Vladimir Kim, Minhyuk Sung (* co-first authors)
CVPR 2024
Project arXiv PDF Code

InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion

Jihyun Lee, Shunsuke Saito, Giljoo Nam, Minhyuk Sung, Tae-Kyun Kim
CVPR 2024
Project

Split, Merge, and Refine: Fitting Tight Bounding Boxes via Learned Over-Segmentation and Iterative Search

Chanhyeok Park, Minhyuk Sung
3DV 2024
arXiv

SyncDiffusion: Coherent Montage via Synchronized Joint Diffusions

Yuseung Lee, Kunho Kim, Hyunjin Kim, Minhyuk Sung
NeurIPS 2023
Project arXiv PDF Code Hugging Face

FourierHandFlow: Neural 4D Hand Representation Using Fourier Query Flow

Jihyun Lee, Junbong Jang, Donghwan Kim, Minhyuk Sung, Tae-Kyun Kim
NeurIPS 2023
Project arXiv

OptCtrlPoints: Optimizing Control Points for Biharmonic 3D Shape Deformation

Kunho Kim, Mikaela Angelina Uy, Despoina Paschalidou, Alec Jacobson, Leonidas Guibas, Minhyuk Sung
Pacific Graphics 2023 (Full Paper)
Project arXiv PDF Slides Video

SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulation

Juil Koo*, Seungwoo Yoo*, Minh Hieu Nguyen*, Minhyuk Sung (* equal contributions)
ICCV 2023
Project arXiv PDF Code Hugging Face 3Dpresso (Text-to-3D)

Im2Hands: Learning Attentive Implicit Representation of Interacting Two-Hand Shapes

Jihyun Lee, Minhyuk Sung, Honggyu Choi, Tae-Kyun Kim
CVPR 2023
Project arXiv

ShapeTalk: A Language Dataset and Framework for 3D Shape Edits and Deformations

Panos Achlioptas, Ian Huang, Minhyuk Sung, Sergey Tulyakov, Leonidas Guibas
CVPR 2023
Project PDF

Seg&Struct: The Interplay Between Part Segmentation and Structure Inference for 3D Shape Parsing

Junghyun Kim, Kaichun Mo, Minhyuk Sung*, Woontack Woo* (* co-corresponding authors)
WACV 2023 (Algorithm Track)
Project arXiv Poster Video

LADIS: Language Disentanglement for 3D Shape Editing

Ian Huang, Panos Achlioptas, Tianyi Zhang, Sergei Tulyakov, Minhyuk Sung, Leonidas Guibas
Findings of EMNLP 2022
arXiv PDF Code

The Shape Part Slot Machine: Contact-based Reasoning for Generating 3D Shapes from Parts

Kai Wang, Paul Guerrero, Vladimir Kim, Siddhartha Chaudhuri, Minhyuk Sung, Daniel Ritchie
ECCV 2022
arXiv Code

PartGlot: Learning Shape Part Segmentation from Language Reference Games

Juil Koo, Ian Huang, Panos Achlioptas, Leonidas Guibas, Minhyuk Sung
CVPR 2022 (Oral)
Project arXiv Video Code

Pop-Out Motion: 3D-Aware Image Deformation via Learning the Shape Laplacian

Jihyun Lee*, Minhyuk Sung*, Hyunjin Kim, Tae-Kyun Kim (* equal contributions)
CVPR 2022
Project arXiv Video Code

Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinders

Mikaela Angelina Uy*, Yen-yu Chang*, Minhyuk Sung, Purvi Goel, Joseph Lambourne, Tolga Birdal, Leonidas Guibas (* equal contributions)
CVPR 2022
Project arXiv Poster Video Code

Implicit LiDAR Network: LiDAR Super-Resolution via Interpolation Weight Prediction

Youngsun Kwon, Minhyuk Sung*, Sung-Eui Yoon* (* co-corresponding authors)
ICRA 2022
Project arXiv PDF Code

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 Web Demo Supplementary Code

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 contributions)
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 contributions)
ECCV 2020
Project arXiv Slides Code

Learning and Exploring the Compositional Structure of 3D Data

Minhyuk Sung
Ph.D. 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 contributions)
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
Project arXiv PDF Slides Code

ComplementMe: Weakly-Supervised Component Suggestions for 3D Modeling

Minhyuk Sung, Hao Su, Vladimir G. Kim, Siddhartha Chaudhuri, Leonidas Guibas
SIGGRAPH Asia 2017 (Featured in an ACM press release)
Project arXiv PDF Slides Code Media 1 Media 2