Jinsun Park

Jinsun Park, Ph.D.

Post-doctoral Researcher
Robotics and Computer Vision Laboratory
School of Electrical Engineering
Korea Advanced Institute of Science and Technology (KAIST)

E-mail : zzangjinsun_at_gmail.com / zzangjinsun_at_kaist.ac.kr

[CV] [LinkedIn] [Google Scholar] [Github]

Research Interests

Multi-Modal Sensor System
Computer Vision
Deep Learning
Depth Completion

News

Jun. 2021 : One paper is accepted in RAL (with IROS)
Dec. 2020 : Winner, Qualcomm Innovation Fellowship Korea (QIFK) 2020
Nov. 2020 : One paper is accepted in SPL
Jul. 2020 : One paper is accepted in ECCV 2020
Feb. 2020 : One paper is accepted in CVPR 2020
Jul. 2019 - Jan. 2020 : Research Intern @ HikVision Research America (with Dr. Zhe Hu)
Sep. 2019 : One paper is accepted in WACV 2020
Jun. 2019 : Two papers are accepted in IROS 2019

Academic Activities

Reviewer
IEEE Transactions on Image Processing (TIP) : 2020
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) : 2018, 2020, 2021
IEEE International Conference on Computer Vision (ICCV) : 2021
IEEE Winter Conference on Applications of Computer Vision (WACV) : 2020
Asian Conference on Computer Vision (ACCV) : 2018

International Journals

2021

RAL_IROS21_MS_UDA_Teaser MS-UDA: Multi-Spectral Unsupervised Domain Adaptation for Thermal Image Semantic Segmentation
Yeong-Hyeon Kim, Ukcheol Shin, Jinsun Park and In So Kweon
IEEE Robotics and Automation Letters (RAL), Jun 2021
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Sep 2021

[Paper] [Bibtex] [Project Page (Code and Dataset)]

2020

SPL20_SPKD_Teaser Lightweight Deep CNN for Natural Image Matting via Similarity-Preserving Knowledge Distillation
Donggeun Yoon*, Jinsun Park* and Donghyeon Cho [* Equal Contribution]
IEEE Signal Processing Letters (SPL), Nov 2020
[Paper] [Bibtex] [Project Page (Code)]

2019

TPAMI18_PS_RF_Teaser Depth from a Light Field Image with Learning-based Matching Costs
Hae-Gon Jeon, Jaesik Park, Gyeongmin Choe, Jinsun Park, Yunsu Bok, Yu-Wing Tai and In So Kweon
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Feb 2019
[Paper] [Bibtex]

2018

PRL18_Teaser Efficient Adaptive Non-Maximal Suppression Algorithms for Homogeneous Spatial Keypoint Distribution
Oleksandr Bailo, Francois Rameau, Kyungdon Joo, Jinsun Park, Oleksandr Bogdan and In So Kweon
Pattern Recognition Letters (PRL), Apr 2018
[Paper] [Bibtex] [Project Page (Code)]

International Conferences

2020

ECCV20_NLSPN Non-Local Spatial Propagation Network for Depth Completion
Jinsun Park, Kyungdon Joo, Zhe Hu, Chi-Kuei Liu and In So Kweon
European Conference on Computer Vision (ECCV), Aug 2020
[Winner, Qualcomm Innovation Fellowship Korea (QIFK) 2020]
[Paper] [Bibtex] [Project Page (Code)]


CVPR20_RefSR Robust Reference-based Super-Resolution with Similarity-Aware Deformable Convolution
Gyumin Shim, Jinsun Park and In So Kweon
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2020
[Paper] [Bibtex] [Project Page]

WACV20_PASSD Propose-and-Attend Single Shot Detector
Ho-Deok Jang, Sanghyun Woo, Philipp Benz, Jinsun Park and In So Kweon
IEEE Winter Conference on Applications of Computer Vision (WACV), Mar 2020
[Paper] [Bibtex]


2019

IROS19_Sensor Vehicular Multi-Camera Sensor System for Automated Visual Inspection of Electric Power Distribution Equipment
Jinsun Park, Ukcheol Shin, Gyumin Shim, Kyungdon Joo, Francois Rameau, Junhyeok Kim, Dong-Geol Choi and In So Kweon
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Nov 2019
[Paper] [Bibtex]

IROS19_AE Camera Exposure Control for Robust Robot Vision with Noise-Aware Image Quality Assessment
Ukcheol Shin, Jinsun Park, Gyumin Shim, Francois Rameau and In So Kweon
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Nov 2019
[Paper] [Bibtex] [Project Page (Code & Dataset)]

2017

ICCV17_Teaser Weakly- and Self-Supervised Learning for Content-Aware Deep Image Retargeting
Donghyeon Cho, Jinsun Park, Tae-Hyun Oh, Yu-Wing Tai and In So Kweon
IEEE International Conference on Computer Vision (ICCV), Oct 2017 [Spotlight Presentation]
[Paper] [Bibtex]

CVPR17_Teaser A Unified Approach of Multi-scale Deep and Hand-crafted Features for Defocus Estimation
Jinsun Park, Yu-Wing Tai, Donghyeon Cho and In So Kweon
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jul 2017
[Paper] [Bibtex] [Project Page (Code)]

2016

URAI16_Teaser Asymmetric stereo with catadioptric lens: High quality image generation for intelligent robot
Donghyeon Cho, Jinsun Park, Yu-Wing Tai and In So Kweon
International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), Aug 2016
[Paper] [Bibtex]

2015

CVPR15_Teaser Accurate Depth Map Estimation from a Lenslet Light Field Camera
Hae-Gon Jeon, Jaesik Park, Gyeongmin Choe, Jinsun Park, Yunsu Bok, Yu-Wing Tai and In So Kweon
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2015
[Paper] [Bibtex] [Project Page (Code)]


Other Publications

2018

FCV18_Teaser Real-time Demonstration of Collaborative Localization of a Swarm of Connected Vehicles
Francois Rameau, Oleksandr Bailo, Jinsun Park, Kyungdon Joo, Jaesung Choe and In So Kweon
International Workshop on Frontiers of Computer Vision (FCV), Feb 2018 [Best Demo Presentation Award]
[Paper] [Bibtex] [Certificate]

2017

CVPRW17_Teaser A Taxonomy and Evaluation of Dense Light Field Depth Estimation Algorithms
Ole Johannsen, Katrin Honauer, Bastian Goldluecke, Anna Alperovich, Federica Battisti, Yunsu Bok, Michele Brizzi, Marco Carli, Gyeongmin Choe, Maximilian Diebold, Marcel Gutsche, Hae-Gon Jeon, In So Kweon, Jaesik Park, Jinsun Park, Hendrik Schilling, Hao Sheng, Lipeng Si, Michael Strecke, Antonin Sulc, Yu-Wing Tai, Qing Wang, Ting-Chun Wang, Sven Wanner, Zhang Xiong, Jingyi Yu, Shuo Zhang and Hao Zhu
IEEE Conference on Computer Vision and Pattern Recognition Workshop - Light Fields for Computer Vision (CVPRW - LF4CV), Jul 2017
[Paper] [Bibtex]

FCV17_Teaser Single Image Depth Estimation using Convolutional Neural Networks with NCC-based Loss
Jinsun Park and In So Kweon
International Workshop on Frontiers of Computer Vision (FCV), Feb 2017
[Paper] [Bibtex]