Kihwan Yoon
A5052587213- Advanced Image Processing Techniques
- Advanced Vision and Imaging
- Image and Signal Denoising Methods
- Photoacoustic and Ultrasonic Imaging
- Advanced Fluorescence Microscopy Techniques
- Image Processing Techniques and Applications
- Image and Video Quality Assessment
- Video Coding and Compression Technologies
- Optical Coherence Tomography Applications
- Image Enhancement Techniques
University of Seoul
2023-2024
Korea Electronics Technology Institute
2022-2023
University of Würzburg
2023
This paper introduces a novel benchmark for efficient up-scaling as part of the NTIRE 2023 Real-Time Image Super-Resolution (RTSR) Challenge, which aimed to upscale images from 720p and 1080p resolution native 4K (×2 ×3 factors) in real-time on commercial GPUs. For this, we use new test set containing diverse ranging digital art gaming photography. We assessed methods devised SR by measuring their runtime, parameters, FLOPs, while ensuring minimum PSNR fidelity over Bicubic interpolation....
Single-image super-resolution technology has become a topic of extensive research in various applications, aiming to enhance the quality and resolution degraded images obtained from low-resolution sensors. However, most existing studies on single-image have primarily focused developing deep learning networks operating high-performance graphics processing units. Therefore, this study proposes lightweight real-time image network for 4K images. Furthermore, we applied reparameterization method...
Single-image super-resolution technology has been widely studied in various applications to improve the quality and resolution of degraded images acquired from noise-sensitive low-resolution sensors. As most studies on single-image focused development deep learning networks operating high-performance GPUs, this study proposed an efficient lightweight network that enables real-time performance mobile devices. To replace relatively slow element-wise addition layer devices, we introduced a skip...
This paper introduces a novel benchmark as part of the AIS 2024 Real-Time Image Super-Resolution (RTSR) Challenge, which aims to upscale compressed images from 540p 4K resolution (4x factor) in real-time on commercial GPUs. For this, we use diverse test set containing variety ranging digital art gaming and photography. The are using modern AVIF codec, instead JPEG. All proposed methods improve PSNR fidelity over Lanczos interpolation, process under 10ms. Out 160 participants, 25 teams...
The subjective image quality of the Video Frame Interpolation (VFI) result depends on whether features such as edges, textures and blobs are preserved. With development deep learning, various algorithms have been proposed objective results VFI significantly improved. Moreover, perceptual loss has used in a method that enhances by preserving image, result, is Despite enhancements achieved VFI, no analysis performed to preserve specific interpolated frames. Therefore, we conducted an textural...