Suhyeon Ha

I am a PhD student in the School of Computing at KAIST, advised by Prof. Sung-Eui Yoon, working in the Scalable Graphics, Vision, & Robotics Lab.

I earned my BS and ME in Computer Science and Engineering from Chung-Ang University, researching under Prof. Junseok Kwon in the Computer Vision Machine Learning Lab. I have also interned at LG AI Research.

Email  /  Google Scholar  /  Github  /  CV

Recent News


Research Experience


Publications


Conference

UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and UnFavOrable Sets
Youngju Na, Woo Jae Kim, Kyu Beom Han, Suhyeon Ha, Sung-Eui Yoon
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
project page / paper / code

UFORecon, a robust view-combination generalizable surface reconstruction under arbitrary and unfavorable input views

Attentive Style Transfer with Target Feature Palette
Suhyeon Ha, Guisik Kim, Junseok Kwon
Women in Computer Vision Workshop, 16th European Conference on Computer (ECCVW) , 2020
Oral Presentation (in the Top 3 of submissions)
paper / code

Bidirectional Deep Residual learning for Haze Removal
Guisik Kim, Jinhee Park, Suhyeon Ha, Junseok Kwon
Vision for all Seasons Workshop, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPRW), 2019
paper

Adaptive patch based convolutional neural network for robust dehazing
Guisik Kim, Suhyeon Ha, Junseok Kwon
The 25th IEEE International Conference on Image Processing (ICIP), 2018
paper

Journal

Style Transfer with Target Feature Palette and Attention Coloring
Suhyeon Ha, Guisik Kim, Junseok Kwon
Multimedia Tools and Application, 81(27), 39675-39694, 2022
paper

Visual Tracking Enhancement by Trajectory Simulation based on Hidden Semi-Markov Model
Suhyeon Ha and Junseok Kwon
Electronics Letters , vol. 56, no. 2, Jan, page 85-87, 2020
paper

Awards and Honors


  • Top 3 papers at ECCV Workshop on Women in Computer Vision
    2020
  • Silver Prize at 30th Image Processing and Image Understanding
    2018

Modified from Zhendong Wang