Cascaded 2D-to-3D Multi-view Consistency for 3D Gaussian Splatting from Two Blurry Images
Under Review, 2026
* Equal contribution
Paper Project Code
Haeyun Choi
I am an incoming Ph.D. student in the School of Data Science at the University of Virginia, advised by Prof. Cheng Peng and Prof. Lei Li. Before beginning my Ph.D., I am working as a Research Scientist at KT R&D Center on vision-language-action (VLA) model development. I received my M.S. in Artificial Intelligence from POSTECH, where I was a member of the Computer Graphics Lab advised by Prof. Sunghyun Cho.
My research interests lie broadly in computer vision and computer graphics, with a focus on building visual systems for real-world scenarios. I am particularly interested in 3D scene representation and neural rendering under challenging conditions such as blur, noise, and sparse observations. More broadly, I aim to develop reliable visual intelligence systems at the intersection of vision, graphics, multimodality, and generative models.
News
Aug. 2026
I will begin my Ph.D. at the University of Virginia School of Data Science.
Mar. 2025
I joined KT R&D Center as a Research Scientist.
Feb. 2025
I received my M.S. in Artificial Intelligence from POSTECH.
Feb. 2025
DeepDeblurRF received the Outstanding Paper Award at IPIU 2025.
Feb. 2025
A paper (DeepDeblurRF) is accepted to CVPR 2025.
Publications
✓ hover to play
✓ hover to play
