Hakyeong Kim (김하경)
Hakyeong Kim (김하경)
Embedded Files
I am a PhD student at KAIST Visual Computing Lab (VCLab), supervised by professor Min H. Kim. Before working at KAIST VCLab, I earned BS and MS degree in Computer Science from KAIST.
My research focuses on reconstructing and understanding the 3D world from images and sensors — spanning 3D scene reconstruction, depth sensing, and neural rendering. I'm broadly interested in problems where computer vision, computational photography, and deep learning intersect to make machines see and interpret the physical world more accurately.
Updates;
Paper accepted at CVPR 2026
Internship at Microsoft Research Asia in Beijing (2025.06-2025.12)
Visiting research fellow in Brown university (2024.06 - 2024.11)
[CV] pdf
[Google scholar] link
[E-Mail] hkkim@vclab.kaist.ac.kr
[Linked in] 🔗 LinkedIn
Publications
Publications
Dense Metric Depth Completion from Sparse Direct Time-of-Flight Sensors
Dense Metric Depth Completion from Sparse Direct Time-of-Flight Sensors
Hakyeong Kim, Ruicheng Wang, Chengtang Yao, Jiaolong Yang, Min H. Kim
Proc. IEEE/CVF Computer Vision and Pattern Recognition
(CVPR 2026) [paper] [project page] [code]
OmniSDF: Scene Reconstruction using Omnidirectional Signed Distance Functions and Adaptive Binoctrees
OmniSDF: Scene Reconstruction using Omnidirectional Signed Distance Functions and Adaptive Binoctrees
Hakyeong Kim, Andreas Meuleman, Hyeonjoong Jang, James Tompkin, Min H. Kim
Proc. IEEE/CVF Computer Vision and Pattern Recognition
(CVPR 2024) [paper] [project page]
FloatingFusion: Depth from ToF and Image-stabilized Stereo Cameras
FloatingFusion: Depth from ToF and Image-stabilized Stereo Cameras
Andreas Meuleman, Hakyeong Kim, James Tompkin, Min H. Kim
Proc. European Conference on Computer Vision
(ECCV 2022) [paper] [project page]
High-Quality Stereo Image Restoration from Double Refraction
High-Quality Stereo Image Restoration from Double Refraction
Hakyeong Kim, Andreas Meuleman, Daniel S. Jeon, Min H. Kim
Proc. IEEE Computer Vision and Pattern Recognition
(CVPR 2021) [paper] [project page]
View-dependent Scene Appearance Synthesis using Inverse Rendering from Light Fields
View-dependent Scene Appearance Synthesis using Inverse Rendering from Light Fields
Dahyun Kang, Daniel S. Jeon, Hakyeong Kim, Hyeonjoong Jang, Min H. Kim
Proc. IEEE International Conference on Computational Photography
(ICCP 2021) [paper] [project page]
Page updated
Google Sites
Report abuse