Ph. D. candidate
Department of ECE, SNU, Seoul, Korea
Google scholar: profile
I am a Ph.D student majoring in computer vision at SNU computer vision lab, advised by prof. Kyoung Mu Lee.
I am interested in deep learning and low-level computer vision problems, especially visual quality enhancement.
My recent research topics include deblurring, super-resolution, neural network acceleration.
- Conference reviewer: CVPR, ICCV, ECCV, SIGGRAPH Asia
- Journal reviewer: IJCV, TIP, TMM, TNNLS, TVCJ, STSP, SPL
- Workshop co-organizer: NTIRE 2019, 2020, 2021, AIM 2019, 2020
Awards and Honors
- Outstanding reviewer: ECCV 2020
- Outstanding reviewer: ICCV 2019
- Highly cited paper award: Department of ECE, SNU, 2018
- Challenge winner & best paper: NTIRE 2017 Challenge on Single Image Super-Resolution
- I’m co-organizing the 6th NTIRE workshop and challenges in conjunction with CVPR 2021. I, Sanghyun Son, Suyoung Lee are in charge of image deblurring and video super-resolution challenge tracks. Image Deblurring Track 1. Low Resolution, Track 2. JPEG artifacts, Video Super-Resolution Track 1. Spatial, Track 2. Spatio-Temporal.
- I’m co-organizing the 2nd AIM workshop and challenges in conjunction with ECCV 2020. Sanghyun Son, I and Jaerin Lee are in charge of Video Temporal Super-Resolution Challenge.
- I’m co-organizing the 5th NTIRE workshop and challenges in conjunction with CVPR 2020. I and Sanghyun Son are in charge of Image/Video Deblurring challenge tracks. Track 1: Image deblurring, Track 2: Image deblurring on mobile devices, Track 3: Video deblurring.
- I’m co-organizing the 1st AIM workshop and challenges in conjunction with ICCV 2019. I and Sanghyun Son are in charge of Video Temporal Super-Resolution Challenge.
- REDS dataset for video deblurring/super-resolution is available!
- I co-organized the 4th NTIRE workshop and challenges in conjunction with CVPR 2019. Many thanks to my colleagues, Sungyong Baik, Seokil Hong, Gyeongsik Moon, Sanghyun Son, Radu Timofte and Kyoung Mu Lee for collecting, processing and releasing the REDS dataset together.