H
Haesol Park
Researcher at Systems Research Institute
Publications - 12
Citations - 236
Haesol Park is an academic researcher from Systems Research Institute. The author has contributed to research in topics: Computer science & Deblurring. The author has an hindex of 7, co-authored 8 publications receiving 189 citations. Previous affiliations of Haesol Park include Seoul National University.
Papers
More filters
Journal ArticleDOI
Look Wider to Match Image Patches With Convolutional Neural Networks
Haesol Park,Kyoung Mu Lee +1 more
TL;DR: A novel convolutional neural network module to learn a stereo matching cost with a large-sized window that can successfully utilize the information from a large area without introducing the fattening effect is proposed.
Proceedings ArticleDOI
Joint Estimation of Camera Pose, Depth, Deblurring, and Super-Resolution from a Blurred Image Sequence
Haesol Park,Kyoung Mu Lee +1 more
TL;DR: This paper proposes a pioneering unified framework that solves four problems simultaneously, namely, dense depth reconstruction, camera pose estimation, super-resolution, and deblurring, by reflecting a physical imaging process and solving the cost minimization problem using an alternating optimization technique.
Journal ArticleDOI
GPU-friendly multi-view stereo reconstruction using surfel representation and graph cuts
TL;DR: A new surfel (surface element) based multi-view stereo algorithm that runs entirely on GPU that utilizes more accurate photo-consistency and reconstructs the 3D shape up to sub-voxel accuracy.
Journal ArticleDOI
Look Wider to Match Image Patches with Convolutional Neural Networks
Haesol Park,Kyoung Mu Lee +1 more
TL;DR: Huang et al. as mentioned in this paper proposed a pyramid-pooling layer to learn a stereo matching cost with a large-sized window, which can successfully utilize the information from a large area without introducing the fattening effect.
Book ChapterDOI
Joint Blind Motion Deblurring and Depth Estimation of Light Field
TL;DR: A novel algorithm to estimate all blur model variables jointly, including latent sub-aperture image, camera motion, and scene depth from the blurred 4D light field, achieves high quality light field deblurring and depth estimation simultaneously under arbitrary 6-DOF camera motion and unconstrained scene depth.