Hyeonjun Sim

Senior Camera Systems Engineer at Qualcomm in San Diego

E-mail: flhy5836@gmail.com

[CV] [Google Scholar] [LinkedIn] [GitHub]

Research Interests

Deep Learning, Low-level Computer Vision, Image/Video Processing, Restoration: Super-Resolution, Video Frame Interpolation, Deblurring, Video Depth estimation, Bayer Denoising

Education

Ph.D., School of Electrical Engineering, KAIST

Advised by Prof. Munchurl Kim at Video and Image Computing Lab.

M.S., Department of Industrial & Systems Engineering, KAIST

B.S., Department of Mathematical Sciences, cum laude, KAIST

Chungbuk Science High School

Mar. 2018 - Aug. 2022

Mar. 2016 - Feb. 2018

Mar. 2011 - Feb. 2016

Mar. 2009 - Feb. 2011

News

Sep. 2022 - Joined Qualcomm.

Publications

Modernizing Old Photos Using Multiple References via Photorealistic Style Transfer

A. Gunawan, S. Y. Kim, H. Sim, J.-H. Lee, M. Kim

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023

[ProjectPage] [Paper] [arXiv] [8min_video]

XVFI: eXtreme Video Frame Interpolation

H. Sim*, J. Oh*, M. Kim (* equal contribution)

IEEE International Conference on Computer Vision (ICCV), 2021

(Oral presentation, 3% of submitted papers)

[Paper] [arXiv] [GitHub] [Demo] [12min_video]

KOALAnet: Blind Super-Resolution using Kernel-Oriented Adaptive Local Adjustment

S.Y. Kim*, H. Sim*, M. Kim (* equal contribution)

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021

[Paper] [arXiv] [GitHub] [5min_video]

Breaking Moravec's Paradox: Visual-Based Distribution in Smart Fashion Retail

S.W. Sung, H. Baek, H. Sim, E.H. Kim, H. Hwangbo, Y.J. Jang

The fifth international workshop on fashion and KDD, 2020

[arXiv]

A Deep Motion Deblurring Network based on Per-Pixel Adaptive Kernels with Residual Down-Up and Up-Down Modules

H. Sim, M. Kim

IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2019.

3rd Place Award in NTIRE 2019 Challenge on Video Deblurring

[Paper] [GitHub]

NTIRE 2019 Challenge on Video Deblurring: Methods and Results

S. Nah, R. Timofte, [and 43 others, including H. Sim]

IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2019.

[Paper]

High-Resolution Image Dehazing with respect to Training Losses and Receptive Field Sizes

H. Sim, S. Ki, J-S. Choi, S.Y. Kim, S. Seo, S. Kim, M. Kim

IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018.

4th Place Award (2nd Rank in Outdoor Track, 4th Rank in Indoor Track) in NTIRE 2018 Challenge on Image Dehazing

[Paper]

Fully End-to-End learning based Conditional Boundary Equilibrium GAN with Receptive Field Sizes Enlarged for Single Ultra-High Resolution Image Dehazing

S. Ki, H. Sim, J-S. Choi, S.Y. Kim, S. Seo, S. Kim, M. Kim

IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018.

[Paper]

NTIRE 2018 Challenge on Image Dehazing: Methods and results

C. Ancuti, C. O. Ancuti, R. Timofte, [and 62 others, including H. Sim]

IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018.

[Paper]

Honors and Awards

NTIRE 2019 Challenge on Video Deblurring in conjunction with CVPR 2019
- 3rd Place Award, Long Beach, US, June 2019.
NTIRE 2018 Challenge on Image Dehazing in conjunction with CVPR 2018
- 4th Place Award (2nd Rank in Outdoor Track, 4th Rank in Indoor Track), Salt Lake City, US, June 2018.
2017 The 13th KMAC Management Innovation Research Paper and Case Study Contest
- Excellence Award - Title : A study on deep learning-based fashion product recommendation method in online shopping malls