Curriculum Vitae
Jihyong Oh
I am an Assistant Professor at Graduate School of Advanced Imaging Science, Multimedia & Film (GSAIM) at Chung-Ang University (CAU), and I have been leading the Creative Vision and Multimedia Lab (CMLab) since Sep. 2023. Before that, I was a post-doctoral researcher at VICLAB. I received Ph.D. degree (Feb. 2023) and MS degree (Feb. 2019) advised by Prof. Munchurl Kim (VICLAB) at the School of Electrical Engineering in KAIST. I was a research intern at Meta.
I primarily focus on a variety of deep-learning-based Computer Vision research areas. I pursue to newly define problems targeted for real-world applications.
Updated on 5 APR 2024.
Contacts
If you are interested in collaborating with me or in joining CMLab, please don't hesitate to send the email below.
E-mail: jhoh94@gmail.com or jihyongoh@cau.ac.kr
[#511, 305 Building] 84, Heukseok-ro, Dongjak-gu, Seoul, 06974, South Korea (Google Map)
[CMLab] [CV(pdf)] [Google Scholar] [GitHub] [LinkedIn]
Research Interests
Neural Radiance Fields (NeRF)
Video Frame Interpolation / Super Resolution / Deblurring / Colorization
Optical Flow Estimation, Computational Photography, Inverse Tone Mapping
Generative AI; Diffusion Models, GANs
GAN/CNN-based Synthetic Aperture Radar (SAR) Target Recognition/Generation
Research Experiences
SEP 2023 - Present
Post-doctoral Researcher, VICLAB (Video & Image Computing Lab), Daejeon, South Korea APR 2023 - AUG 2023
Topic: Dynamic NeRF & Low-level Computer Vision
Topic: Video View Synthesis using Large-Motion Dynamic NeRF (LDNeRF)
International Publications
DyBluRF 🫨: Dynamic Deblurring Neural Radiance Fields for Blurry Monocular Video
Minh-Quan Viet Bui*, Jongmin Park*, Jihyong Oh☨ and Munchurl Kim☨
(*equal contribution, ☨co-corresponding authors)
(under review) arXiv 2024.
[arXiv2024] [Project Page] [GitHub (will be updated)] [Demo] [Video7mins]
🍎 FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurring
Geunhyuk Youk, Jihyong Oh☨ and Munchurl Kim☨. (☨co-corresponding authors)
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, Oral Presentation.
(🏅Oral Paper Rate: 0.78% ≈ 90/11532, Acceptance Rate: 23.6% ≈ 2719/11532)
[arXiv2024] [Project Page] [GitHub (★: 487)] [Demo] [Video6mins]
DeMFI: Deep Joint Deblurring and Multi-Frame Interpolation with Flow-Guided Attentive Correlation and Recursive Boosting
Jihyong Oh and Munchurl Kim
European Conference on Computer Vision (ECCV), 2022.
(Acceptance Rate: 28% ≈ 1650/5803 )
[ECCV2022] [Supp] [GitHub (★: 79)] [Demo] [Poster] [Video5mins]
XVFI: eXtreme Video Frame Interpolation
Hyeonjun Sim*, Jihyong Oh* and Munchurl Kim (*equal contribution)
IEEE/CVF International Conference on Computer Vision (ICCV), 2021, Oral Presentation.
(🏅Oral Paper Rate: 3%, Acceptance Rate: 25.9% ≈ 1617/6236)
[arXiv] [ICCV2021] [Supp] [GitHub (★: 261)] [X4K1000FPS] [Demo] [Oral12mins] [Flowframes(GUI)] [Poster]
PeaceGAN: A GAN-based Multi-Task Learning Method for SAR Target Image Generation with a Pose Estimator and an Auxiliary Classifier
Jihyong Oh and Munchurl Kim
Remote Sensing (IF=5.0)
vol. 13, issue 19: 3939, Oct. 2021 (DOI: https://doi.org/10.3390/rs13193939)
SPAM-Net: A CNN-based SAR Target Recognition Network with Pose Angle Marginalization Learning
Jihyong Oh*, Gwang-Young Youm* and Munchurl Kim (*equal contribution)
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT) (IF=8.4)
vol. 31, issue 2, pp. 701-714, Feb. 2021. (DOI: 10.1109/TCSVT.2020.2987346)
FISR: Deep Joint Frame Interpolation and Super-Resolution with a Multi-Scale Temporal Loss
Soo Ye Kim*, Jihyong Oh* and Munchurl Kim (*equal contribution)
AAAI Conference on Artificial Intelligence (AAAI), 2020.
(Acceptance Rate: 20.6% ≈ 1591/7737 )
[Paper] [GitHub (★: 74)] [Poster] [Spotlight-PPT]
JSI-GAN: GAN-Based Joint Super-Resolution and Inverse Tone-Mapping with Pixel-Wise Task-Specific Filters for UHD HDR Video
Soo Ye Kim*, Jihyong Oh* and Munchurl Kim (*equal contribution)
AAAI Conference on Artificial Intelligence (AAAI), 2020.
(Acceptance Rate: 20.6% ≈ 1591/7737 )
[Paper] [GitHub (★: 59)] [Poster] [Spotlight-PPT]
Deep SR-ITM: Joint Learning of Super-Resolution and Inverse Tone-Mapping for 4K UHD HDR Applications
Soo Ye Kim, Jihyong Oh and Munchurl Kim
IEEE/CVF International Conference on Computer Vision (ICCV), 2019, Oral Presentation.
(🏅Oral Paper Rate: 4 %, Acceptance Rate: 25% ≈ 1077/4303)
Domestic Publications (South Korea)
Jihyong Oh and Munchurl Kim, “SAR Image Generation based on GAN with an Auxiliary Classifier," 2018 한국군사과학기술학회 (KIMST) 창립 20주년 종합학술대회
Gwang-Young Youm, Jihyong Oh and Munchurl Kim, “A Deep Convolution Network for Fast SAR Automatic Target Detection and Recognition," 2018 한국군사과학기술학회 (KIMST) 창립 20주년 종합학술대회
Educational History
Ph.D., KAIST - School of Electrical Engineering 03.2019 - 02.2023
Advisor: prof. Munchurl Kim, G.P.A: 4.2 (121 credits completed, including those of M.S.)
M.S., KAIST - School of Electrical Engineering 03.2017 - 02.2019
Advisor: prof. Munchurl Kim, G.P.A: 4.17 (53 credits completed)
B.S., KAIST - School of Electrical Engineering 02.2012 - 02.2017
G.P.A: 3.75 (141 credits completed)
Cum Laude
Minor: Business and Technology Management
Daejeon Science High School (DSHS) 03.2010 - 02.2012
Early graduation (2years)
Work Experiences
Electronic Telecommunication Research Institute (ETRI)
Intern, Electroencephalography (EEG) Signal Processing, 01.2016 - 02.2016 (2 months)
Reviewer Services
Journal: IEEE TGRS, IEEE TIP, IEEE Access
Conference: CVPR2021/2022/2023/2024, ICCV2021/2023, ECCV2022, SIGGRAPH2024, AAAI2021
Award
Outstanding Reviewer Award: ICCV2021 (top 5%)
Project Experiences (as Research Assistant)
SW STAR LAB (IITP) 04.2022 - 08.2023
Deep Learning-based Rendering of Spatial Video with Stationary and Dynamic Scenes (Project co-lead)
Institute for Information & communications Technology Promotion (IITP) 02.2019 - 02.2023
Deep Joint Deblurring and Multi-Frame Interpolation (Project lead)
Extreme Video Frame Interpolation (Project co-lead)
Deep Joint Frame Interpolation and Super-Resolution (Project co-lead)
GAN-based Joint Super-Resolution and Inverse Tone-Mapping (Project co-lead)
SK Telecom Co., Ltd. (SKT) 05.2021 - 02.2022
Deep 3:2 Pull-Down for Conversion of 24fps to 30fps (Project lead)
Center for Applied Research in Artificial Intelligence (CARAI) 12.2019 - 02.2021
Multi-modal Fusion Learning for Soldier/Unit Behavior Recognition (Support)
SK Telecom Co., Ltd. (SKT) 05.2019 - 02.2020
GAN-based automatic video colorization (Project lead)
Agency for Defense Development (ADD) 07.2017 - 12.2018
SAR Target Recognition with CNNs (Project lead)
Information Technology Research Center (ITRC) 07.2017 - 12.2018
SAR Automatic Target Recognition (ATR) with CNNs, SAR Image Generation with GANs (Project lead)
LG Electronics Co., Ltd. 01.2017 - 12.2017
Implementation of Fast computation of DCT and DST (Support)
Patents
KR102342526: Method and Apparatus for Video Colorization, 12.2021
KR102345760: Target Recognizing Method and Apparatus, 12.2021
KR102307622: Deep Joint Frame Processing Method and Apparatus Apparatus for Performing Frame Interpolation, Super-Resolution or Inverse Tone Mapping, 09.2021
KR102214502: Image Joint Processing Method and Apparatus, 02.2021
KR102075745: Method and Apparatus for Estimating Target Pose, 02.2020
Activities
Young Researcher Session Talk
Title: "Handling Real-World Videos in Computer Vision Tasks"
20 mins, IPIU2024, hosted by Prof. Hak Gu Kim, 02.01.2024.
Invited Talk
Title: "Handling Real-World Videos in Computer Vision Tasks"
1 hour, Sungkyunkwan University (SKKU), hosted by Prof. Eun-Seok Ryu, 08.05.2023.
[in Graduate School]
Invited Talk
Title: "A Study on SAR: CNN/GAN-based methods for SAR applications"
1 hour, Korea Aerospace Research Institute (KARI), 22.05.2019
Teaching Assistant (TA) in KAIST
EE432 Digital Signal Processing - Spring 2020, Spring 2019, Spring 2018
EE838B Special Topics in Image Engineering <Special Topic on Image Engineering: Advanced Image Restoration and Quality Enhancement>- Fall 2020
EE898 Special Topics in Intelligent Information Processing <Deep Learning Technology for Computer Vision and Robotics> - Spring 2021
EE210A Probability and Introductory Random Processes - Spring 2021
Counseling Assistant (CA) in KAIST for 3 semesters
About any personal concern: college life, study, club activity, research, relationship, romance, sports, graduate school, career etc.
[in Undergraduate School]
Exchange Student Program
Technische Universität Berlin (TUB), 09.2014 - 02.2015 (6 months)
German level A1
Private Lessons (Teaching)
Subjects - Mathematics (middle & high school students) & Physics (high school students), 2012 - 2017 (6 years)
Model of KAIST (MOKA)
Club - student model for homepages/news of KAIST, 2012 - 2015 (3 years)
Multidisciplinary Capstone Design (KAIST course title)
Noise Compact Detector, work with SM Instruments (SMI), Fall 2016
KAIST Family Science Camp
Mentor, three times, KAIST Global Institute For Talented EDucation (GIFTED)
Exhibitions
ITRC Forum 2019 24.04 - 27.04.2019
Topic (software demo.) : A GAN-based Multi-Task Learning Method for SAR Target Image Generation at desired pose angles of target classes
Host Institution : Ministry of Science and ICT
Pangyo Future Forum 20.02.2019
Topic (poster) : SR-FPGA, ITM-CNN, Fast Algorithms for SAR ATD/ATR (several topics of VIC Lab.)
Host Institution : Artificial Intelligence Industry Association (AIIA)
ITRC Forum 2018 23.05 - 26.05.2018
Topic (poster) : Deep learning-based algorithms for multi-polarization SAR target recognition
Host Institution : Ministry of Science and ICT
Defense Research Achievement Promotion Exhibition 23.03.2018
Topic (poster) : Deep learning-based algorithm for SAR ATD/ATR
Sponsor: Poongsan, Hanwha System, LIG Nex1
Host Institution : KAIST, Agency for Defense Development (ADD)
Computer Skills
Programming Languages: PyTorch, Tensorflow, Python, MATLAB, C
OS: Windows/Ubuntu
Etc.: Word, PowerPoint, Excel, Visio, LaTeX, Adobe Premiere Pro CC, PyCharm, FFmpeg, GitHub