Introduction

I am Seungwook Kim, a highly self-motivated PhD candidate mainly researching on (1) visual correspondences between 2D images or 3D point clouds (and their applications), (2) 2D/3D Equivariance, and (3) {Text,Image}-to-{3D,Video} Generation. I am under the supervision of professor Minsu Cho in the POSTECH Computer Vision Lab.

Education

Integrated MSc/PhD in Graduate School of AI

2020 - 2026 (expected)
POSTECH

Under the supervision of professor Minsu Cho.

  • Graduate School of AI research Excellent Paper Award, 2021, 2023
  • POSTECHIAN Fellowship (Leadership) 2022
  • (Emergency) Reviewer for: CVPR, ECCV, ICCV, NeurIPS, ICML, TPAMI, 3DV, WACV, ACCV (2022-24)

BSc in Computer Sciences & Engineering

2015 - 2020
POSTECH
  • Cumulative GPA: 3.70 / 4.3
  • Jigok Scholarship (Full scholarship)
  • Student Mentoring Program Scholarship (Monthly scholarship)
  • On-school Work Scholarship (Per-semester scholarship)

Experiences

PhD Intern / Data-Intelligent Creation-Vision and Graphics team

09.2023 - 02.2024
ByteDance, CA, USA

Technical Chair

05.2024 - 12.2024
ACCV, Hanoi, Vietnam
  • (Expected to have) Managed the Microsoft CMT for coordinating paper submission and reviewing process.

Undergraduate Intern / 3D Map construction from LiDAR

03.2020 - 37.2020
Polaris3D, Pohang, South Korea
  • Implemented the process of retrieving data from Intel Realsense cameras to Jetson Nano in real-time.
  • Merged the two streams of data from two different angles to output a 3D map in real-time.

Undergraduate Intern / Camera ISP

12.2019 - 01.2020
SK Hynix, Icheon, South Korea
  • Analyzed the image post-processing algorithms applied to raw images obtained from senseors.
  • Identified an imbalance in the dark corners (vignetting) of a raw image from a sensor under development.

Undergraduate Intern / AI team

06.2019 - 08.2019
Netmarble, Seoul, South Korea
  • Developed prior speech-to-3D lip synthesis pipeline to be light-weight (mobile-runnable) using TensorFlow.
  • Accepted to Korea Software Congress 2019 (VOL 46 NO. 02 PP. 1690 ~ 1692 2019. 12)

Undergraduate Intern / Data Engineering & Analysis team

02.2018 — 12.2018
Dable, Seoul, South Korea
  • Analyzed heavy-traffic raw data collected at AWS RedShift using PostgreSQL.
  • Developed batch codes that run regularly on the AWS RedShift to output processed data on a MySQL server.
  • Analyzed processed data using MySQL.
  • Developed web crawling system to identify potential blog clients.

Publications

List of publications which have been accepted / are under review for international journals and conferences.

  • 3D Geometric Shape Assembly via Efficient Point Cloud Matching
  • Nahyuk Lee*, Juhong Min*, Junha Lee, Seungwook Kim, Kanghee Lee, Jaesik Park, Minsu Cho
    The 41st International Conference on Machine Learning (ICML) 2024 @ Vienne
  • Multi-view Image Prompted Multi-view Diffusion for Improved 3D Generation
  • Seungwook Kim, Yichun Shi, Kejie Li, Minsu Cho, Peng Wang
    Arxiv 2024
  • Enhancing 3D Fidelity of Text-to-3D using Cross-View Correspondences
  • Seungwook Kim, Kejie Li, Xueqing Deng, Yichun Shi, Minsu Cho, Peng Wang
    The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) 2024 @ Seattle
  • Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transform
  • Chunghyun Park*, Seungwook Kim*, Jaesik Park, Minsu Cho
    The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) 2024 @ Seattle
  • Efficient Semantic Matching with Hypercolumn Correlation (Best paper finalist)
  • Seungwook Kim, Juhong Min, Minsu Cho
    IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024 @ Big Island
  • Stable and Consistent Prediction of 3D Characteristic Orientation via Invariant Residual Learning
  • Seungwook Kim*, Chunghyun Park, Yoonwoo Jeong, Jaesik Park, Minsu Cho
    International Conference on Machine Learning (ICML) 2023 @ Honolulu Presented as talk @ KETI (Korean Electronics Technology Institute)
  • Learning Rotation-Equivariant Features for Visual Correspondence
  • Jongmin Lee, Byungjin Kim, Seungwook Kim, Minsu Cho
    The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) 2023 @ Vancouver
  • Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondence
  • Juhong Min, Seungwook Kim, Minsu Cho
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2023
  • SeLCA: Self-Supervised Learning of Canonical Axis
  • Seungwook Kim, Yoonwoo Jeong, Chunghyun Park, Jaesik Park, Minsu Cho
    Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS) 2022 Workshop - Symmetry and Geometry in Neural Representations @ New Orleans Presented as talk @ SAIT (Samsung Advanced Institute of Technology)
  • TransforMatcher: Match-to-Match Attention for Semantic Correspondence
  • Seungwook Kim, Juhong Min, Minsu Cho
    The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) 2022 @ New Orleans Presented as talk @ KETI (Korean Electronics Technology Institute), SAIT (Samsung Advanced Institute of Technology), KCCV (Korean Conference on Computer Vision)
  • Deep Hough Voting for Robust Global Registration
  • Junha Lee, Seungwook Kim, Minsu Cho, Jaesik Park
    The IEEE / CVF International Conference on Computer Vision (ICCV) 2021 @ Montreal
  • Learning to Distill Convolutional Features into Compact Local Descriptors
  • Jongmin Lee, Yoonwoo Jeong, Seungwook Kim, Juhong Min, Minsu Cho
    IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2021 @ Hawaii

    Skills & Proficiency

    Python & PyTorch

    C & C++

    PostgreSQL & MySQL & RedShift

    HTML5 & CSS