Recent News

07 / 2024 We are releasing the source code for HCBlur.
05 / 2024 Our paper on hybrid camera deblurring (HCBlur) is accepted to SIGGRAPH 2024.
04 / 2024 We are releasing the source code for ParamISP.
02 / 2024 Our paper on RAW reconstruction (ParamISP) is accepted to CVPR 2024.
04 / 2023 I am joining Samsung AI Center Toronto as a research scientist.
02 / 2023 I won the CSE Outstanding Research Award and Best Dissertation Award from POSTECH.
10 / 2022 We are releasing the source code for RT-VDBLR.
08 / 2022 Our paper on real-time video deblurring (RT-VDBLR) is accepted to PG 2022.
07 / 2022 We are releasing the source code for RSBlur.
07 / 2022 Our paper on realistic blur synthesis (RSBlur) is accepted to ECCV 2022.
04 / 2022 Demos for RefVSR are released (CPU and GPU models).
03 / 2022 We are releasing the source code for RefVSR.
03 / 2022 Our paper on reference-based video super-resolution (RefVSR) is accepted to CVPR 2022.

PublicationsPermalink

2024

HDR_before
Input
HDR_after
Deblurred

Deep Hybrid Camera Deblurring for Smartphone Cameras

Jaesung Rim, Junyong Lee, Heemin Yang, Sunghyun Cho

ACM SIGGRAPH, Denver, CO, US, 2024

HDR_before
Input (LDR)
HDR_after
Output (HDR)

ParamISP: Learned Forward and Inverse ISPs using Camera Parameters

*Woohyeok Kim, *Geonu Kim, Junyong Lee, Seungyong Lee, Seung-Hwan Baek, Sunghyun Cho

IEEE Computer Vision and Pattern Recognition (CVPR), Seattle, WA, US, 2024

2023

phd_thesis

Learning Image and Video Restoration Using Auxiliary Data

Junyong Lee

Ph.D. Dissertation, Computer Science and Engineering, POSTECH, 2023

🏆 Best Dissertation Award (IT Division, POSTECH)

🏆 CSE Outstanding Research Award (Dept. of CSE, POSTECH)

2022

PVDNet_before
Input
PVDNet_after
Deblurred

Real-Time Video Deblurring via Lightweight Motion Compensation

*Hyeongseok Son, *Junyong Lee, Sunghyun Cho, Seungyong Lee (*equal contribution)

Pacific Graphics (PG), Kyoto, Japan, 2022 (special issue of the Computer Graphics Forum (CGF))

RealBlur_before
Input
RealBlur_after
Deblurred

Realistic Blur Synthesis for Learning Image Deblurring

Jaesung Rim, Geonung Kim, Jungeon Kim, Junyong Lee, Seungyong Lee, Sunghyun Cho

European Conference on Computer Vision (ECCV), Tel Aviv, Israel, 2022

RefVSR

Reference-based Video Super-Resolution Using Multi-Camera Video Triplets

Junyong Lee, Myeonghee Lee, Sunghyun Cho, Seungyong Lee

IEEE Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, US, 2022

2021

KPAC_before
Input
KPAC_after
Deblurred

Single Image Defocus Deblurring Using Kernel-Sharing Parallel Atrous Convolutions

Hyeongseok Son, Junyong Lee, Sunghyun Cho, Seungyong Lee

IEEE International Conference on Computer Vision (ICCV), Virtual, 2021

PVDNet_before
Input
PVDNet_after
Deblurred

Recurrent Video Deblurring with Blur-Invariant Motion Estimation and Pixel Volumes

Hyeongseok Son, Junyong Lee, Jonghyeop Lee, Sunghyun Cho, Seungyong Lee

ACM Transactions on Graphics (TOG), 2021 (Presented at SIGGRAPH 2021)

IFAN_before
Input
IFAN_after
Deblurred

Iterative Filter Adaptive Network for Single Image Defocus Deblurring

Junyong Lee, Hyeongseok Son, Jaesung Rim, Sunghyun Cho, Seungyong Lee

IEEE Computer Vision and Pattern Recognition (CVPR), Virtual, 2021

2020

CTHA_before
Input & target
CTHA_after
Color transferred

Deep Color Transfer using Histogram Analogy

Junyong Lee, Hyeongseok Son, Gunhee Lee, Jonghyeop Lee, Sunghyun Cho, Seungyong Lee

Computer Graphics International (CGI), Virtual, 2020 (special issue of The Visual Computer)

2019

DMENet_before
Input
DMENet_after
Defocus map

Deep Defocus Map Estimation using Domain Adaptation

Junyong Lee, Sungkil Lee, Sunghyun Cho, Seungyong Lee

IEEE Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, US, 2019