Hui Yong Kim

Prof. Hui Yong Kim


Research Focus & Metrics

Academic Career Length

23Years (2004-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 August 2023 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
YKYeongwoong Kim
Yeongwoong Kim
HJHyewon Jeong
Hyewon Jeong
JYJanghyun Yu
Janghyun Yu
YKYounhee Kim
Younhee Kim
JLJooyoung Lee
Jooyoung Lee
HKHui Yong Kim
Hui Yong Kim
The proliferation of deep learning-based machine vision applications has given rise to a new type of compression, so called video coding for machine (VCM). VCM differs from traditional video coding in that it is optimized for machine vision performance instead of human visual quality. In the feature compression track of MPEG-VCM, multi-scale features extracted from images are subject to compression. Recent feature compression works have demonstrated that the versatile video coding (VVC) standard-based approach can achieve a BD-rate reduction of up to 96% against MPEG-VCM feature anchor. However, it is still sub-optimal as VVC was not designed for extracted features but for natural images. Moreover, the high encoding complexity of VVC makes it difficult to design a lightweight encoder without sacrificing performance. To address these challenges, we propose a novel multi-scale feature compression method that enables both the end-to-end optimization on the extracted features and the design of lightweight encoders. The proposed model combines a learnable compressor with a multi-scale feature fusion network so that the redundancy in the multi-scale features is effectively removed. Instead of simply cascading the fusion network and the compression network, we integrate the fusion and encoding processes in an interleaved way. Our model first encodes a larger-scale feature to obtain a latent representation and then fuses the latent with a smaller-scale feature. This process is successively performed until the smallest-scale feature is fused and then the encoded latent at the final stage is entropy-coded for transmission. The results show that our model outperforms previous approaches by at least 52% BD-rate reduction and has ×5 to ×27 times less encoding time for object detection. It is noteworthy that our model can attain near-lossless task performance with only 0.002-0.003% of the uncompressed feature data size.

25 May 2016 in IEEE Transactions on Broadcasting
Verified
Journal Article
Closed access
QHQin Huang
Qin Huang
SJSe Yoon Jeong
Se Yoon Jeong
SYShanglin Yang
Shanglin Yang
DZDichen Zhang
Dichen Zhang
SHSudeng Hu
Sudeng Hu
CKC.-C. Jay Kuo
C.-C. Jay Kuo
Video of higher frame rates (HFR) reduces the visual artifact in large screen display at the cost of a higher coding bit rate (or transmission bandwidth). In this work, we propose a perceptual quality driven frame rate selection (PQD-FRS) method that assigns a time-varying frame rate to a sequence so as to reduce its transmission cost. The objective of the PQD-FRS method is to offer perceptually indistinguishable experience for a certain percentage of viewers. We first conduct a subjective test to characterize the relationship between human perceived quality and video contents, and build a frame-rate-dependent video quality assessment dataset to serve as the ground truth. Then, we use a machine learning approach for the design of the key module of the PQD-FRS method, called the “satisfied user ratio (SUR) prediction.” The SUR prediction module predicts the percentage of satisfied viewers, who cannot differentiate video quality of a lower and HFR, using the support vector regression. It is confirmed by experimental results that the proposed SUR module can offer a so highly accurate prediction that the PQD-FRS system can dynamically assign a proper frame rate to video without any perceptual quality degradation for a majority of viewers.

1 April 2017
Verified
Conference Paper
Closed access
QHQin Huang
Qin Huang
HWHaiqiang Wang
Haiqiang Wang
SLSung Chang Lim
Sung Chang Lim
HKHui Yong Kim
Hui Yong Kim
SJSe Yoon Jeong
Se Yoon Jeong
CKC.-C. Jay Kuo
C.-C. Jay Kuo
Evaluation of coding efficiency is traditionally modeled as a continuous rate-distortion (R-D) function, where the peak signal-to-noise ratio (PSNR) is adopted as the quality measure. Although the PSNR-versus-bitrate curve offers some useful tradeoff information between video quality and coding bit-rates, it does not take human perceptual experience into account. In this work, by following the recent image/video quality assessment framework based on the just-noticeable-difference (JND) notion, we conduct a subjective test for HEVC (High Efficiency Video Codec) video to measure the QP value that lies in the boundary of perceptually lossless and lossy coded bit streams for each human subject. This is also known as the first JND point. It is observed that the statistics of the first JND points of 30 subjects follows the normal distribution for a great majority of test sequences. Finally, a machine-learning approach is proposed to predict the mean of the group-based JND distribution based on extracted video features. It is shown by experimental results that the mean JND point can be predicted accurately.

28 May 2021 in IEEE Access
Verified
Journal Article
Open access
HKHyunseok Ko
Hyunseok Ko
HKHui Yong Kim
Hui Yong Kim
With the aid of rapid development in optical and display devices, Holography has become an emerging technology to represent 3D objects providing the most natural and realistic depth illusion to the users. To reproduce a light field of objects, a hologram records the interference patterns between the object and reference wavefields. Especially for computer-generated holograms, they contain vast amount of data and must be efficiently compressed for storage or transmission. Although several coding solutions, including standardized compression tools and their variations, have been tried in the literature, the coding efficiency is not satisfactory because holograms have completely different unique properties from those observed in natural images, whereas the legacy coding solutions are optimized for the latter. In this work, we propose a deep-learning based image compression network for phase-only holograms. The proposed network is trained in an end-to-end manner with the help of data augmentation technique and aims at minimizing the entropy of the input hologram. In comprehensive experiments, we demonstrate that our compression network shows the state-of-the-art coding performance that even surpasses the latest compression standard Versatile Video Coding by up to 39% in terms of BD-rate gain. Furthermore, we provide in-depth analysis for experimental results in both holographic and numerical reconstruction domains, such as individual performances of the test codecs, a performance comparison with different objective image fidelity metrics, and subjective quality evaluation results.

8 September 2016 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
QHQin Huang
Qin Huang
HKHui Yong Kim
Hui Yong Kim
WTWen-Jiin Tsai
Wen-Jiin Tsai
SJSe Yoon Jeong
Se Yoon Jeong
JCJin Soo Choi
Jin Soo Choi
CKC.-C. Jay Kuo
C.-C. Jay Kuo
A contour-like artifact called false contour is often observed in large smooth areas of decoded images and video. Without loss of generality, we focus on detection and removal of false contours resulting from the state-of-the-art High Efficiency Video Coding codec. First, we identify the cause of false contours by explaining the human perceptual experiences on them with specific experiments. Next, we propose a precise pixel-based false contour detection method based on the evolution of a false contour candidate (FCC) map. The number of points in the FCC map becomes fewer by imposing more constraints step by step. Special attention is paid to separating false contours from real contours such as edges and textures in the video source. Then, a decontour method is designed to remove false contours in the exact contour position while preserving edge/texture details. Extensive experimental results are provided to demonstrate the superior performance of the proposed false contour detection and removal method in both compressed images and videos.

27 February 2023 in Optics Express
Verified
Journal Article
Closed access
KOKwan-Jung Oh
Kwan-Jung Oh
HBHyunmin Ban
Hyunmin Ban
SCSeungmi Choi
Seungmi Choi
HKHyunseok Ko
Hyunseok Ko
HKHui Yong Kim
Hui Yong Kim
Compressing digital holograms have growing attention nowadays due to their huge amount of original data sizes. Although many progresses have been reported for full-complex holograms, the coding performance for phase-only holograms (POHs) has been quite limited so far. In this paper, we present a very efficient compression method for POHs. It extends the conventional video coding standard HEVC (High Efficiency Video Coding) in such a way that the standard can be able to compress not only the natural images but also the phase images effectively. First, we suggest a proper way to calculate differences, distances and clipped values for phase signals by considering the inherent periodicity of phases. Then, some of the HEVC encoding and decoding processes are modified accordingly. The experimental results show that the proposed extension significantly outperforms the original HEVC for POH video sequences; specifically, average BD-rate reductions of 63.3% and 65.5% are achieved in phase domain and numerical reconstruction domain, respectively. It is worth mentioning that the modified encoding & decoding processes are very minimal and also applicable to the VVC (Versatile Video Coding), which is a successor of the HEVC.