Junyong Lee

Recent News

08 / 2022	Our paper on real-time video deblurring is conditionally 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.
02 / 2022	I've been selected for the Samsung Ph.D. sponsorship program at SAIT.
12 / 2021	I've been selected for Qualcomm Innovation Fellowship, 2021 South Korea Finalist.
08 / 2021	We are releasing the source code for KPAC.
07 / 2021	Our paper on defocus deblurring (KPAC) is accepted to ICCV 2021.
06 / 2021	We are releasing the source code for IFAN.
Previous news ▽
06 / 2021	We are releasing the source code for PVDNet.
03 / 2021	Demos for DMENet and IFAN are released.
03 / 2021	Our paper on video deblurring (PVDNet) is accepted to TOG 2021.
03 / 2021	Our paper on defocus deblurring (IFAN) is accepted to CVPR 2021.
12 / 2020	We received the presentation award for our paper on defocus deblurring at KSC 2020.
10 / 2020	We are releasing the source code for CTHA.
09 / 2020	Our paper on color transfer using histogram analogy (CTHA) is accepted to CGI 2020.
11 / 2019	I won Naver Ph.D. Fellowship Award.
06 / 2019	We are releasing the source code for DMENet and SYNDOF.
03 / 2019	Our paper on defocus map estimation is accepted to CVPR 2019.

PublicationsPermalink

2022

Real-Time Video Deblurring via Lightweight Motion Compensation

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

Pacific Graphics (PG), Kyoto, Japan, 2022

arXiv BibTeX Code will be released soon

@InProceedings{Rim2022RSBlur,
    author    = {Hyeongseok Son and Junyong Lee and Sunghyun Cho and Seungyong Lee},
    title     = {Real-Time Video Deblurring via Lightweight Motion Compensation},
    booktitle = {Pacific Graphics},
    year      = {2022},
}

[TOP] 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

Project Paper arXiv Supp Code BibTeX

@InProceedings{Rim2022RSBlur,
    author    = {Jaesung Rim and Geonung Kim and Jungeon Kim and Junyong Lee and Seungyong Lee and Sunghyun Cho},
    title     = {Realistic Blur Synthesis for Learning Image Deblurring},
    booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
    year      = {2022},
}

[TOP] 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

Project Paper arXiv Supp Poster Video Slide Demo Code BibTeX

@InProceedings{Lee2022RefVSR,
    author    = {Junyong Lee and Myeonghee Lee and Sunghyun Cho and Seungyong Lee},
    title     = {Reference-based Video Super-Resolution Using Multi-Camera Video Triplets},
    booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    year      = {2022},
}

2021

[TOP] 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

Paper arXiv Supp Poster Slide Code BibTeX

@InProceedings{Son2021KPAC,
    author    = {Hyeongseok Son and Junyong Lee and Sunghyun Cho and Seungyong Lee},
    title     = {Single Image Defocus Deblurring Using Kernel-Sharing Parallel Atrous Convolutions},
    booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
    year      = {2021}
}

[TOP] 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)

Paper arXiv Supp Slide Code BibTeX

@Article{Son2021PVDNet,
    author  = {Hyeongseok Son and Junyong Lee and Jonghyeop Lee and Sunghyun Cho and Seungyong Lee},
    title   = {Recurrent Video Deblurring with Blur-Invariant Motion Estimation and Pixel Volumes},
    journal = {ACM Transactions on Graphics (TOG)},
    volume  = {40},
    number  = {5},
    year    = {2021}
}

[TOP] 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

Project Paper arXiv Supp Poster Video Slide Demo Code BibTeX

@InProceedings{Lee2021IFAN,
    author    = {Junyong Lee and Hyeongseok Son and Jaesung Rim and Sunghyun Cho and Seungyong Lee},
    title     = {Iterative Filter Adaptive Network for Single Image Defocus Deblurring},
    booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    year      = {2021}
}

2020

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)

Project Paper Supp Video Slide Code BibTeX

@Article{Lee2020CTHA,
    author  = {Junyong Lee and Hyeongseok Son and Gunhee Lee and Jonghyeop Lee and Sunghyun Cho and Seungyong Lee},
    title   = {Deep Color Transfer using Histogram Analogy},
    journal = {The Visual Computer},
    volume  = {36},
    number  = {10},
    pages   = {2129--2143},
    year    = {2020},
}

2019

[TOP] 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

Project Paper Supp Poster Demo Code BibTeX

@InProceedings{Lee2019DMENet,
    author    = {Junyong Lee and Sungkil Lee and Sunghyun Cho and Seungyong Lee},
    title     = {Deep Defocus Map Estimation Using Domain Adaptation},
    booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    year      = {2019}
}