News

Apr 2, 2020

I am currently looking for full-time job opportunities and postdoc positions in US and Canada. Please feel free to drop me an email to contact me!

Mar 20, 2020

Our paper “Learning the Loss Functions in a Discriminative Space for Video Restoration” has been uploaded to arXiv.

Sep 4, 2019

Our paper “Unsupervised Keypoint Learning for Guiding Class-Conditional Video Prediction” has been accepted to NeurIPS 2019!

Bio

I'm a Computer Science Ph.D. candidate at Yonsei University, advised by Prof. Seon Joo Kim. My research interests focus on Computer Vision and Machine Learning. Particularly, I'm interested in improving various aspects of photography using machine learning and learning visual data with minimal supervision.
In the summer of 2018, I interned at Snap Research under the supervision of Chongyang Ma. I also worked with Ning Xu at Adobe Research.
For more information, please refer to my CV.

  • NAVER Ph.D. Fellowship
    NAVER Corporation
    2017
  • Excellent Paper Award
    Dept. of CS, Yonsei University
    2016
  • Bronze Prize
    22nd Samsung HumanTech Paper Award
    2016
  • Global Ph.D. Fellowship
    National Research Foundation of Korea
    2015-2019

Publication

Learning the Loss Functions in a Discriminative Space for Video Restoration

Younghyun Jo, Jaeyeon Kang, Seoung Wug Oh, Seonghyeon Nam, Peter Vajda, Seon Joo Kim
arXiv
[pdf]

Unsupervised Keypoint Learning for Guiding Class-Conditional Video Prediction

Yunji Kim, Seonghyeon Nam, In Cho, Seon Joo Kim
Proc. Advances in Neural Information Processing Systems (NeurIPS) 2019
[pdf]  [github]  [media]

End-to-End Time-Lapse Video Synthesis from a Single Outdoor Image

Seonghyeon Nam, Chongyang Ma, Menglei Chai, William Brendel, Ning Xu, Seon Joo Kim
Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019
[pdf] [supp]

Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language

Seonghyeon Nam, Yunji Kim, Seon Joo Kim
Proc. Advances in Neural Information Processing Systems 32 (NeurIPS) 2018
[Spotlight (168/4856, acceptance rate 3.5%)]
[pdf] [supp]  [github]  [bibtex]

Modelling the Scene Dependent Imaging in Cameras with a Deep Neural Network

Seonghyeon Nam, Seon Joo Kim
Proc. of International Conference on Computer Vision (ICCV) 2017
[pdf] [supp]  [bibtex]

Deep Semantics-Aware Photo Adjustment

Seonghyeon Nam, Seon Joo Kim
arXiv
[pdf]

A Holistic Approach to Cross-Channel Image Noise Modeling and its Application to Image Denoising

Seonghyeon Nam*, Youngbae Hwang*, Yasuyuki Matsushita, Seon Joo Kim
Proc. of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016
[Spotlight (acceptance rate 9.7%)]
[pdf]  [project page]  [bibtex]