Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Keunsoo Ko"'
Autor:
Keunsoo Ko, Changgyun Kim
Publikováno v:
Applied Sciences, Vol 14, Iss 22, p 10332 (2024)
During hydrogen refueling, the data values determining the state of charge (SoC) of a vehicle can be missing due to internal and external factors. This causes inaccurate SoC estimation, resulting in oversupply or undersupply. To overcome this issue,
Externí odkaz:
https://doaj.org/article/2ab3cd43d9c44d679b0f6a58b03fec2e
Publikováno v:
IEEE Access, Vol 11, Pp 46707-46718 (2023)
Face super-resolution involves generating a high-resolution facial image from a low-resolution one. It is, however, quite a difficult task when the resolution difference between input and output images is too large. In order to tackle this challenge,
Externí odkaz:
https://doaj.org/article/21667afc413647dd92fee445a2fa126d
Autor:
Keunsoo Ko, Chang-Su Kim
Publikováno v:
IEEE Access, Vol 10, Pp 98981-98992 (2022)
Contrast enhancement is required in many applications. Many studies have been conducted to perform contrast enhancement automatically, but most of them do not consider various personal preferences for contrast. We propose an edge-aware interactive co
Externí odkaz:
https://doaj.org/article/fe010b2da12f4575bee6fa986e1ae0f7
Publikováno v:
IEEE Access, Vol 9, Pp 169321-169334 (2021)
Face super-resolution is a domain-specific super-resolution task to generate a high-resolution facial image from a low-resolution one. In this paper, we propose a novel face super-resolution network, called CollageNet, to super-resolve an input image
Externí odkaz:
https://doaj.org/article/0bc9276984154c828796751f41607f40
Autor:
Keunsoo Ko, Chang-Su Kim
Publikováno v:
IEEE Access, Vol 9, Pp 168342-168354 (2021)
A CNN-based interactive contrast enhancement algorithm, called IceNet, is proposed in this paper, which enables a user to adjust image contrast easily according to his or her preference. Specifically, a user provides a parameter for controlling the g
Externí odkaz:
https://doaj.org/article/71903d5c259a4b6cb060726b76028c0e
Publikováno v:
IEEE Network. 35:177-183
Computer vision tasks such as object detection are crucial for the operations of autonomous vehicles (AVs). Results of many tasks, even those requiring high computational power, can be obtained within a short delay by offloading them to edge clouds.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4285a7ba783fd97032752155ee99ac1e
https://doi.org/10.1109/mnet.011.2000248
https://doi.org/10.1109/mnet.011.2000248
Publikováno v:
IEEE Transactions on Image Processing. 30:4114-4128
A novel light field super-resolution algorithm to improve the spatial and angular resolutions of light field images is proposed in this work. We develop spatial and angular super-resolution (SR) networks, which can faithfully interpolate images in th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::96c157ed92e8fd4554f0ff1cdc7119c4
https://doi.org/10.1109/tip.2021.3069291
https://doi.org/10.1109/tip.2021.3069291
Publikováno v:
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 31
A lightweight blind image denoiser, called blind compact denoising network (BCDNet), is proposed in this paper to achieve excellent trade-offs between performance and network complexity. With only 330K parameters, the proposed BCDNet is composed of t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6acecd918998c6828cfbdbaec4ae7af9
https://pubmed.ncbi.nlm.nih.gov/35085080
https://pubmed.ncbi.nlm.nih.gov/35085080
Publikováno v:
ICIP
A novel approach for image demosaicking based on adaptive lattice-aware filter (ALF) and global refinement unit (GRU) is proposed in this work. We generate ALFs dynamically, which are adaptive to positions of pixels within color lattices in a color f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6d1927a90b781e9a393480d67270b5ef
https://doi.org/10.1109/icip40778.2020.9190936
https://doi.org/10.1109/icip40778.2020.9190936
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585679
ECCV (14)
ECCV (14)
Video interpolation increases the temporal resolution of a video sequence by synthesizing intermediate frames between two consecutive frames. We propose a novel deep-learning-based video interpolation algorithm based on bilateral motion estimation. F
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1ab1de1b071fc4c1565a48e2cdac502e
https://doi.org/10.1007/978-3-030-58568-6_7
https://doi.org/10.1007/978-3-030-58568-6_7
