Kyuha Choi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Kyuha Choi has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Geonung Kim
POSTECH, Pohang, Republic of Korea
2 shared publications - Hyun-Seung Lee
Visual Display Business, Samsung Electronics, Suwon, Republic of Korea
2 shared publications - Janghyeok Han
POSTECH, Pohang, Republic of Korea
2 shared publications - Sunghyun Cho
POSTECH, Pohang, Republic of Korea
2 shared publications - Youngseok Han
Visual Display Business, Samsung Electronics, Suwon, Republic of Korea
2 shared publications - Byungseok Min
Samsung Electronics 129 Samsung‐ro Yeongtong‐gu Suwon‐Si Gyeonggi‐do 16677 South Korea
1 shared publication
Latest Publications
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
HL-OutPaint: Coarse-to-Fine Video Outpainting for High-Resolution Long-Range Videos
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessHL-OutPaint: Coarse-to-Fine Video Outpainting for High-Resolution Long-Range Videos
- Open Access
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
DC-VSR: Spatially and Temporally Consistent Video Super-Resolution with Video Diffusion Prior
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessDC-VSR: Spatially and Temporally Consistent Video Super-Resolution with Video Diffusion Prior
- 18 October 2018
- Published by Wiley in Journal of the Society for Information Display
- Vol. 26 (11) , 660-669
Quantitative evaluation method of visual display resolution based on human visual perception
As a manner of evaluating visual display resolution, contrast modulation has been widely used for decades. But, as various types of sub‐pixel layout are adopted for flat panel displays, the contrast modulation metric shows a limitation that it is not consistent with human visual perception on those displays. To overcome this limitation, a new quantitative metric is proposed in this paper by introducing structure comparison and combining it with contrast modulation. Experimental results performed on TV displays with various sub‐pixel structures demonstrate that the proposed metric has higher correlation with perceived visual resolution than the conventional metric.
- 18 October 2018
- Published by Wiley in Journal of the Society for Information Display
- Vol. 26 (11) , 660-669
Quantitative evaluation method of visual display resolution based on human visual perception
As a manner of evaluating visual display resolution, contrast modulation has been widely used for decades. But, as various types of sub‐pixel layout are adopted for flat panel displays, the contrast modulation metric shows a limitation that it is not consistent with human visual perception on those displays. To overcome this limitation, a new quantitative metric is proposed in this paper by introducing structure comparison and combining it with contrast modulation. Experimental results performed on TV displays with various sub‐pixel structures demonstrate that the proposed metric has higher correlation with perceived visual resolution than the conventional metric.
- 1 August 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2010 (1094687X) , 5712-5715
Image resolution improvement based on sinogram super-resolution in PET
One of the limits of PET imaging is the low spatial resolution due to a predetermined detector width. To overcome this limit, we may increase the number of samples by using the wobbling motion. Since the line spread function (LSF) of the sinogram is determined by the detector width, however, the increase of the number of samples is not sufficient to improve the sinogram resolution. In this paper, based on oversampled data obtained from the wobbling motion, we propose a novel and efficient super-resolution (SR) scheme for the sinogram. Since the proposed SR scheme adopts the penalized expectation maximization (EM) algorithm, it guarantees non-negative values of the super-resolved sinogram data. Through the experiments, we demonstrate that the proposed SR scheme can noticeably improve the spatial image resolution.
- 1 August 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2010 (1094687X) , 5712-5715
Image resolution improvement based on sinogram super-resolution in PET
One of the limits of PET imaging is the low spatial resolution due to a predetermined detector width. To overcome this limit, we may increase the number of samples by using the wobbling motion. Since the line spread function (LSF) of the sinogram is determined by the detector width, however, the increase of the number of samples is not sufficient to improve the sinogram resolution. In this paper, based on oversampled data obtained from the wobbling motion, we propose a novel and efficient super-resolution (SR) scheme for the sinogram. Since the proposed SR scheme adopts the penalized expectation maximization (EM) algorithm, it guarantees non-negative values of the super-resolved sinogram data. Through the experiments, we demonstrate that the proposed SR scheme can noticeably improve the spatial image resolution.