About Me

I am a Ph.D. student at VIC Lab, KAIST, advised by Prof. Munchurl Kim. I am expecting to receive my Ph.D. in August 2026.

My research focuses on computer vision, especially image and video restoration (video super-resolution, deblurring, and diffusion-based restoration), with an emphasis on the real-world application perspective.

Video Super-Resolution Video Deblurring Diffusion Models Real-World Restoration

News

  • Jun 2026

    FMA-Net++ and AVSR-Diff accepted to ECCV 2026! 🎉

  • Jun 2025

    PAN-Crafter accepted to ICCV 2025! 🎉

  • Feb 2024

    FMA-Net accepted to CVPR 2024 as an Oral presentation (top 0.8%)! 🎉

Publications

Google Scholar ↗
FMA-Net++ framework
ECCV 2026

FMA-Net++: Motion- and Exposure-Aware Real-World Joint Video Super-Resolution and Deblurring

Geunhyuk Youk, Jihyong Oh†, Munchurl Kim†

In Proceedings of the European Conference on Computer Vision (ECCV), 2026

Paper Project Code
AVSR-Diff framework
ECCV 2026

AVSR-Diff: Scale-Agnostic Diffusion Priors for Temporally Consistent Arbitrary-Scale Video Super-Resolution

Geunhyuk Youk, Jeonghyeok Do, Dayeon Kim, Jihyong Oh†, Munchurl Kim†

In Proceedings of the European Conference on Computer Vision (ECCV), 2026

Paper Project Code
PAN-Crafter framework
ICCV 2025

PAN-Crafter: Learning Modality-Consistent Alignment for PAN-Sharpening

Jeonghyeok Do, Sungpyo Kim, Geunhyuk Youk, Jaehyup Lee†, Munchurl Kim†

In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025

Paper Project Code
FMA-Net framework
CVPR 2024 Oral · Top 0.8%

FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurring

Geunhyuk Youk, Jihyong Oh†, Munchurl Kim†

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

Paper Project Code Video
SAR image translation
IEEE TGRS 2023

Transformer-Based Synthetic-to-Measured SAR Image Translation via Learning of Representational Features

Geunhyuk Youk, Munchurl Kim

IEEE Transactions on Geoscience and Remote Sensing (TGRS), 2023

Paper
CF-SIS 3D point cloud segmentation
ACM MM 2020

CF-SIS: Semantic-Instance Segmentation of 3D Point Clouds by Context Fusion with Self-Attention

Xin Wen, Zhizhong Han, Geunhyuk Youk, Yu-Shen Liu

In Proceedings of the ACM International Conference on Multimedia (ACM MM), 2020

Paper

† Co-corresponding authors.

Academic Service

Conference Reviewer

  • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • Conference on Neural Information Processing Systems (NeurIPS)
  • British Machine Vision Conference (BMVC)

Journal Reviewer

  • IEEE Transactions on Image Processing (TIP)
  • IEEE Transactions on Multimedia (TMM)
  • IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
  • Computer Vision and Image Understanding (CVIU)

Education

Sep 2022 – Aug 2026 (expected)

Ph.D. in Electrical Engineering

KAIST, Korea · Advisor: Prof. Munchurl Kim

Sep 2020 – Jul 2022

M.S. in Electrical Engineering

KAIST, Korea · Advisor: Prof. Munchurl Kim

Sep 2015 – Jul 2019

B.S. in Software Engineering

Tsinghua University, China · Advisor: Prof. Yu-Shen Liu