Assistant Professor Sunghoon Im
He is curently an assistant professor at the department of Information and Communication Engineering at DGIST, South Korea, working as a faculty member of DGIST Computer Vision Lab.
Education
B.S in Electronic Engineering, Sogang University, South Korea (2014)
M.S in Electrical and Electronics, Korea Advanced Institute of Science and Technology (KAIST), South Korea (2016)
Ph.D in Electrical and Electronics, Korea Advanced Institute of Science and Technology (KAIST), South Korea (2019)
Awards
Excellent Student Award, 2018 Rearch Performance Evaluation, KAIST EE, Apr 2019.
Best Poster Award, 2018 Samsung AI Forum, Samsung Research, Sep 2018.
Excellent Intern Award, Microsoft Research Asia (MSRA), Aug 2018.
Honor Student Award, 2017 Reserch Performance Evaluation, KAIST EE, Apr 2018.
Kim Choong-Ki Award, 2016 Reserch Performance Evaluation, KAIST EE, Apr 2017.
Best Poster presentation Award, 29th Workshop on Image Processing and Image Understanding (IPIU), Feb 2017.
Qualcomm Innovation Award 2016, Qualcomm Korea Corp. and KAIST, Apr 2016.
Silver prize, 22nd HumanTech Paper Award, Samsung Electronics Co., Ltd., Feb 2016.
Official Best 10% Paper Selection, ICIP 2015 Organizing Committe, Sep 2015.
Honors
CVPR 2019 Doctoral Consortium, Jun 2019.
ICLR 2019 Travel Award, May 2019.
Microsoft Research Asia (MSRA) Fellowship 2018 Winner, Oct 2018.
International Computer Vision Summer School (ICVSS 2016), Jul 2016.
Global Ph.D Fellowship, National Research Foundation of Korea (about $20,000 + Full scholarship per year for 2+1 years).
Patents
METHOD AND APPARATUS FOR ESTIMATING DEPTH USING RING DIFFERENCE FILTER
Publication date: Sep 28, 2018. (10-2017-0091717)
DEPTH MAP ACQUISITION DEVICE AND DEPTH MAP ACQUISITION METHOD
Publication date: Apr 19, 2018. (10-2016-0103546)
METHOD AND APPARATUS FOR ACQUIRING DEPTH MAP FROM ALL-AROUND CAMERA
Publication date: Apr 17, 2018. (10-2016-0167525)
DEPTH INFORMATION ACQUIRING DEVICE AND METHOD THEREOF
Publication date: Aug 11, 2017. (10-2016-0076766)
APPARATUS AND METHOD FOR DEPTH MAP GENERATION
Publication date: Jun. 02, 2016. (10-2016-0015703)
Selected publications
H. -G. Jeon et al., "A Large-scale Virtual Dataset and Egocentric Localization for Disaster Responses," in IEEE Transactions on Pattern Analysis and Machine Intelligence, doi: 10.1109/TPAMI.2021.3094531.
S. Im, H. Ha, H. -G. Jeon, S. Lin and I. S. Kweon, "Deep Depth from Uncalibrated Small Motion Clip," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 4, pp. 1225-1238, 1 April 2021, doi: 10.1109/TPAMI.2019.2946806.
H. -G. Jeon, J. Surh, S. Im and I. S. Kweon, "Ring Difference Filter for Fast and Noise Robust Depth From Focus," in IEEE Transactions on Image Processing, vol. 29, pp. 1045-1060, 2020, doi: 10.1109/TIP.2019.2937064.
Lee, Seokju, Sunghoon Im, Stephen Lin, and In So Kweon. 2021. “Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency”. Proceedings of the AAAI Conference on Artificial Intelligence 35 (3):1863-72.
For more publications, please visit: https://sunghoonim.github.io/
