Sungjun Yoon

I am an applied research scientist at LG Electronics, working on computer vision and machine learning. My research interests are training a deep neural network (DNN) model for human-centric learning and computational photography, and letting people experience the machine intelligence. Recently, I have been in charge of developing the data plane in the Amazon Elastic Kubernetes Service (EKS) to deploy developed DNN model to the Amazon Web Services (AWS) cloud.

I received the B.S. degree in information and communication engineering from Sejong University, Seoul, South Korea in 2016 and the M.S. degree in electrical engineering from the Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea in 2018.

I read the Originals: How Non-Conformists Move the World in 2017 and was impressed a definition of a word, Vuja De. The meaning of the Vuja De seems to indicate my role for research. I seek to discover new things with a fresh perspective in familiar something.

We face something familiar, but we see it with a fresh perspective that enables us to gain new insights into old problems. — Vuja De in Originals by Adam Grant.

News

Jun 19, 2021	We won the NTIRE 2021 Challenge on Perceptual Image Quality Assessment at the CVPRW 2021.

Selected publications

CVPRW 2021
NTIRE 2021 Challenge on Perceptual Image Quality Assessment

Manri Cheon, Sungjun Yoon, Byungyeon Kang, and Junwoo Lee

IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), Jun. 2021

Abs Bib HTML AWARD

This paper reports on the NTIRE 2021 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2021. As a new type of image processing technology, perceptual image processing algorithms based on Generative Adversarial Networks (GAN) have produced images with more realistic textures. These output images have completely different characteristics from traditional distortions, thus pose a new challenge for IQA methods to evaluate their visual quality. In comparison with previous IQA challenges, the training and testing datasets in this challenge include the outputs of perceptual image processing algorithms and the corresponding subjective scores. Thus they can be used to develop and evaluate IQA methods on GAN-based distortions. The challenge has 270 registered participants in total. In the final testing stage, 13 participating teams submitted their models and fact sheets. Almost all of them have achieved much better results than existing IQA methods, while the winning method can demonstrate state-of-the-art performance.
@inproceedings{jinjin2021iqa, title = {NTIRE 2021 Challenge on Perceptual Image Quality Assessment}, author = {Manri, Cheon and Sungjun, Yoon and Byungyeon, Kang and Junwoo, Lee}, booktitle = {IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW)}, year = {2021}, month = jun, abbr = {CVPRW 2021}, bibtex_show = {true}, html = {https://openaccess.thecvf.com/content/CVPR2021W/NTIRE/html/Gu_NTIRE_2021_Challenge_on_Perceptual_Image_Quality_Assessment_CVPRW_2021_paper.html}, selected = {true}, award = {Award_NTIRE2021.png} }
CVPRW 2020
NTIRE 2020 Challenge on Image Demoireing: Methods and Results

Manri Cheon, Sung-Jun Yoon, Byungyeon Kang, and Junwoo Lee

IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), Jun. 2020

Abs Bib HTML AWARD

This paper reviews the Challenge on Image Demoireing that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2020. Demoireing is a difficult task of removing moire patterns from an image to reveal an underlying clean image. The challenge was divided into two tracks. Track 1 targeted the single image demoireing problem, which seeks to remove moire patterns from a single image. Track 2 focused on the burst demoireing problem, where a set of degraded moire images of the same scene were provided as input, with the goal of producing a single demoired image as output. The methods were ranked in terms of their fidelity, measured using the peak signal-to-noise ratio (PSNR) between the ground truth clean images and the restored images produced by the participants’ methods. The tracks had 142 and 99 registered participants, respectively, with a total of 14 and 6 submissions in the final testing stage. The entries span the current state-of-the-art in image and burst image demoireing problems.
@inproceedings{shanxin2020demoireing, title = {NTIRE 2020 Challenge on Image Demoireing: Methods and Results}, author = {Manri, Cheon and Sung-Jun, Yoon and Byungyeon, Kang and Junwoo, Lee}, booktitle = {IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW)}, year = {2020}, month = jun, abbr = {CVPRW 2020}, bibtex_show = {true}, html = {https://openaccess.thecvf.com/content_CVPRW_2020/html/w31/Yuan_NTIRE_2020_Challenge_on_Image_Demoireing_Methods_and_Results_CVPRW_2020_paper.html}, selected = {true}, award = {Award_NTIRE2020.png} }
IEEE TIP
Hierarchical Extended Bilateral Motion Estimation based Frame Rate Up-Conversion using Learning based Linear Mapping

Sung-Jun Yoon*, Hyun-Ho Kim*, and Munchurl Kim

IEEE Transactions on Image Processing Dec. 2018

Abs Bib HTML

We present a novel and effective learning-based frame rate upconversion (FRUC) scheme, using linear mapping. The proposed learning-based FRUC scheme consists of: 1) a new hierarchical extended bilateral motion estimation (HEBME) method; 2) a light-weight motion deblur (LWMD) method; and 3) a synthesis-based motion-compensated frame interpolation (S-MCFI) method. First, the HEBME method considerably enhances the accuracy of the motion estimation (ME), which can lead to a significant improvement of the FRUC performance. The proposed HEBME method consists of two ME pyramids with a three-layered hierarchy, where the motion vectors (MVs) are searched in a coarse-to-fine manner via each pyramid. The found MVs are further refined in an enhanced resolution of four times by jointly combining the MVs from the two pyramids. The HEBME method employs a new elaborate matching criterion for precise ME which effectively combines a bilateral absolute difference, an edge variance, pixel variances, and an MV difference among two consecutive blocks and its neighboring blocks. Second, the LWMD method uses the MVs found by the HEBME method and removes the small motion blurs in original frames via transformations by linear mapping. Third, the S-MCFI method finally generates interpolated frames by applying linear mapping kernels for the deblurred original frames. In consequence, our FRUC scheme is capable of precisely generating interpolated frames based on the HEBME for accurate ME, the S-MCFI for elaborate frame interpolation, and the LWMD for contrast enhancement. The experimental results show that our FRUC significantly outperforms the state-of-the-art non-deep learning-based schemes with an average of 1.42 dB higher in the peak signal-to-noise-ratio and shows comparable performance with the state-of-the-art deep learning-based scheme.
* Sung-Jun Yoon and Hyun-Ho Kim contribute equally to the work.
@article{sungjun2018FRUC, title = {Hierarchical Extended Bilateral Motion Estimation based Frame Rate Up-Conversion using Learning based Linear Mapping}, author = {Sung-Jun, Yoon* and Hyun-Ho, Kim* and Munchurl, Kim}, journal = {IEEE Transactions on Image Processing}, year = {2018}, month = dec, volume = {27}, issue = {12}, pages = {5918--5932}, numpages = {15}, doi = {10.1109/TIP.2018.2861567}, abbr = {IEEE TIP}, bibtex_show = {true}, html = {https://ieeexplore.ieee.org/document/8423719}, selected = {true} }