Any sufficiently advanced technology is indistinguishable from magic
Arthur C. Clarke
Doyeon Kim
I am an AI researcher at Hyundai Motors Institute of Advanced Technology Development (IATD). Before this, I received my Ph.D. degree from Korea Advanced Institute of Science and Technology (KAIST) advised by Professor Junmo Kim.
[Google Scholar] [github] [CV]
contact: doken111 [at] gmail.com
Research Interest
Deep Learning, Autonomous Driving, Generative Models
Experience
Hyundai Motors Institute of Advanced Technology Development (IATD)
AI Researcher
May 2023 - Current
Education
KAIST, Daejeon, Korea
Ph.D. in Electrical Engineering
2018 - 2023
KAIST, Daejeon, Korea
M.S. in Robotics Program
2016 - 2018
Korea University, Seoul, Korea
B.S. in Computer Science and Engineering
2012 - 2016
Publications
International
Training Cartoonization Network without Cartoon
Doyeon Kim, Dongyeun Lee, Donggyu Joo, Junmo Kim
ICIP 2023
Context-Preserving Two-Stage Video Domain Translation for Portrait Stylization
Doyeon Kim, Eunji Ko, Hyunsu Kim, Junho Kim, Yunji Kim, Dongchan Min, Junmo Kim, Sung Ju Hwang
CVPR Workshop 2023 (AI for Content Creation) [paper]
Fix the Noise: Disentangling Source Feature for Transfer Learning of StyleGAN
Dongyeon Lee, Jae Young Lee, Doyeon Kim, Jaehyun Choi, Junmo Kim
CVPR 2023 (extended version of CVPRW 2022) [paper] [code]
Fix the Noise: Disentangling Source Feature for Transfer Learning of StyleGAN
Dongyeon Lee, Jae Young Lee, Doyeon Kim, Jaehyun Choi, Junmo Kim
CVPR Workshop 2022 (AI for Content Creation, Best Paper Award) [paper]
Linear Combination Approximation of Feature for Channel Pruning
Donggyu Joo, Doyeon Kim, Eojindl Yi, Junmo Kim
CVPR Workshop 2022 (Efficient Deep Learning for Computer Vision) [paper]
Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth
Doyeon Kim, Woonghyun Ga, Pyungwhan Ahn, Donggyu Joo, Sehwan Chun, and Junmo Kim
Arxiv preprint [paper] [code]
TricubeNet: 2D Kernel-Based Object Representation for Weakly-Occluded Oriented Object Detection
Beomyoung Kim, Sihaeng Lee, Janghyeon Lee, Doyeon Kim, and Junmo Kim
WACV 2022 [paper]
Progressive Seed Generation Auto-encoder for Unsupervised Point Cloud Learning
Juyoung Yang, Pyungwhan Ahn, Doyeon Kim, Haeil Lee, and Junmo Kim
ICCV 2021 [paper]
Delivering Meaningful Representation for Monocular Depth Estimation
Doyeon Kim, Donggyu Joo, and Junmo Kim
ICPR 2020 [paper]
Slimming ResNet by Slimming Shortcut
Donggyu Joo, Doyeon Kim, and Junmo Kim
ICPR 2020 [paper]
TiVGAN: Text to Image to Video Generation With Step-by-Step Evolutionary Generator
Doyeon Kim*, Donggyu Joo*, and Junmo Kim (* indicates equal contribution)
Access 2020 [paper]
Leveraging Contextual Information for Monocular Depth Estimation
Doyeon Kim, Sihaeng Lee, Janghyeon Lee, and Junmo Kim,
Access 2020 [paper]
Deep architecture with cross guidance between single image and sparse lidar data for depth completion
Sihaeng Lee, Janghyeon Lee, Doyeon Kim, and Junmo Kim
Access 2020 [paper]
Generating a Fusion Image: One’s Identity and Another’s Shape
Donggyu Joo*, Doyeon Kim*, and Junmo Kim (* indicates equal contribution)
CVPR 2018 [paper]
Improved InfoGAN: Generating High Quality Images with Learning Disentangled Representation
Doyeon Kim, Haechang Jung, Jaeyoung Lee, and Junmo Kim
RiTA 2017
Domestic
Data Synthesis using Convolutional Auto-Encoder
Doyeon Kim, Jeongwoo Ju, and Junmo Kim
IPIU 2017
Honors and Awards
2018 Samsung Human Tech Award, Silver Prize ($7,000)
2016 IT Global Leadership Program Scholarship
2015 National Science Scholarship
2014 Honors Scholarship, College of Informatics Alumni Scholarship