Linwei Zhu

Linwei Zhu


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
23 June 2017 in IEEE Transactions on Broadcasting
Verified
Journal Article
Closed access
LZLinwei Zhu
Linwei Zhu
Yun ZhangYun Zhang
Yun Zhang
ZPZhaoqing Pan
Zhaoqing Pan
RWRan Wang
Ran Wang
KWONG Tak Wu SamKWONG Tak Wu Sam
KWONG Tak Wu Sam
ZPZongju Peng
Zongju Peng
High Efficiency Video Coding (HEVC) improves the compression efficiency at the cost of high computational complexity by using the quad-tree coding unit (CU) structure and variable prediction unit (PU) modes. To minimize the HEVC encoding complexity while maintaining its compression efficiency, a binary and multi-class support vector machine (SVM)-based fast HEVC encoding algorithm is presented in this paper. First, the processes of recursive CU decision and PU selection in HEVC are modeled as hierarchical binary classification and multi-class classification structures. Second, according to the two classification structures, the CU decision and PU selection are optimized by binary and multi-class SVM, i.e., the CU and PU can be predicted directly via classifiers without intensive rate distortion (RD) cost calculation. In particular, to achieve better prediction performance, a learning method is proposed to combine the off-line machine learning (ML) mode and on-line ML mode for classifiers based on a multiple reviewers system. Additionally, the optimal parameters determination scheme is adopted for flexible complexity allocation under a given RD constraint. Experimental results show that the proposed method can achieve 68.3%, 67.3%, and 65.6% time saving on average while the values of Bjøntegaard delta peak signal-to-noise ratio are -0.093dB, -0.091dB, and -0.094dB and the values of Bjøntegaard delta bit rate are 4.191%, 3.842%, and 3.665% under low delay P main, low delay main, and random access configurations, respectively, when compared with the HEVC test model version HM 16.5. Meanwhile, the proposed method outperforms the state-of-the-art fast coding algorithms in terms of complexity reduction and RD performance.

2 March 2023 in ACM Computing Surveys
Verified
Journal Article
Open access
Yun ZhangYun Zhang
Yun Zhang
LZLinwei Zhu
Linwei Zhu
GJGangyi Jiang
Gangyi Jiang
KWONG Tak Wu SamKWONG Tak Wu Sam
KWONG Tak Wu Sam
CKC.-C. Jay Kuo
C.-C. Jay Kuo
To provide users with more realistic visual experiences, videos are developing in the trends of Ultra High Definition (UHD), High Frame Rate (HFR), High Dynamic Range (HDR), Wide Color Gammut (WCG), and high clarity. However, the data amount of videos increases exponentially, which requires high efficiency video compression for storage and network transmission. Perceptually optimized video coding aims to maximize compression efficiency by exploiting visual redundancies. In this article, we present a broad and systematic survey on perceptually optimized video coding. Firstly, we present problem formulation and framework of the perceptually optimized video coding, which includes visual perception modeling, visual quality assessment, and perceptual video coding optimization. Secondly, recent advances on visual factors, computational perceptual models, and quality assessment models are presented. Thirdly, we review perceptual video coding optimizations from four key aspects, including perceptually optimized bit allocation, rate-distortion optimization, transform and quantization, and filtering and enhancement. In each part, problem formulation, working flow, recent advances, advantages, and challenges are presented. Fourthly, perceptual coding performances of the latest coding standards and tools are experimentally analyzed. Finally, challenging issues and future opportunities are identified.

24 June 2019 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
LZLinwei Zhu
Linwei Zhu
KWONG Tak Wu SamKWONG Tak Wu Sam
KWONG Tak Wu Sam
Yun ZhangYun Zhang
Yun Zhang
SWShiqi Wang
Shiqi Wang
XWXu Wang
Xu Wang
In this paper, a novel intra prediction method is proposed to improve the video coding performance, in which the Generative Adversarial Network (GAN) is adopted to intelligently remove the spatial redundancy with the inference process. The proposed GAN based method improves the prediction by exploiting more information and generating more flexible prediction patterns. In particular, the intra prediction is modeled as an inpainting task, which is accomplished with the GAN model to fill in the missing part by conditioning on the available reconstructed pixels. As such, the learned GAN model is incorporated into both video encoder and decoder, and the Rate-Distortion Optimization (RDO) is performed for the competition between GAN based intra prediction and traditional angular based intra prediction to achieve better coding performance. The proposed scheme is implemented into the High Efficiency Video Coding (HEVC) test Model (HM 16.17) and the Versatile Video Coding (VVC) Test Model (VTM 1.1), the experimental results show that the proposed algorithm can achieve 6.6%, 7.5% and 7.5% under HM 16.17 and 6.75%, 7.63% and 7.65% under VTM 1.1 bit rate savings on average for luma and chroma components in the intra coding scenario.

9 November 2017 in IEEE Transactions on Broadcasting
Verified
Journal Article
Closed access
LZLinwei Zhu
Linwei Zhu
Yun ZhangYun Zhang
Yun Zhang
KWONG Tak Wu SamKWONG Tak Wu Sam
KWONG Tak Wu Sam
XWXu Wang
Xu Wang
TZTiesong Zhao
Tiesong Zhao
The latest video compression standard, High Efficiency Video Coding (HEVC), has greatly improved the coding efficiency compared to the predecessor H.264/AVC. However, equipped with the quadtree structure of coding tree unit partition and other sophisticated coding tools, HEVC brings a significant increase in the computational complexity. To address this issue, a coding unit (CU) decision method based on fuzzy support vector machine (SVM) is proposed for rate-distortion-complexity (RDC) optimization, where the process of CU decision is formulated as a cascaded multi-level classification task. The optimal feature set is selected according to a defined misclassification cost and a risk area is introduced for an uncertain classification output. To further improve the RDC performance, different regulation parameters in SVM are adopted and outliers in training samples are eliminated. Additionally, the proposed CU decision method is incorporated into a joint RDC optimization framework, where the width of risk area is adaptively adjusted to allocate flexible computational complexity to different CUs, aiming at minimizing computational complexity under a configurable constraint in terms of RD performance degradation. Experimental results show that the proposed approach can reduce 58.9% and 55.3% computational complexity on average with the values of Bjønteggard delta peak-signal-to-noise ratio as -0.075 dB and -0.085 dB and the values of Bjøntegaard delta bit rate as 2.859% and 2.671% under low delay P and random access configurations, respectively, which has outperformed the state-of-the-art fast algorithms based on statistical information and machine learning.

20 July 2018 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
LZLinwei Zhu
Linwei Zhu
Yun ZhangYun Zhang
Yun Zhang
SWShiqi Wang
Shiqi Wang
HYHui Yuan
Hui Yuan
KWONG Tak Wu SamKWONG Tak Wu Sam
KWONG Tak Wu Sam
HIHorace H.-S. Ip
Horace H.-S. Ip
The quality of synthesized view plays an important role in the 3D video system. In this paper, to further improve the coding efficiency, a convolutional neural network (CNN)-based synthesized view quality enhancement method for 3D high efficiency video coding (HEVC) is proposed. First, the distortion elimination in synthesized view is formulated as an image restoration task with the aim to reconstruct the latent distortion free synthesized image. Second, the learned CNN models are incorporated into 3D HEVC codec to improve the view synthesis performance for both view synthesis optimization (VSO) and the final synthesized view, where the geometric and compression distortions are considered according to the specific characteristics of synthesized view. Third, a new Lagrange multiplier in the rate-distortion cost function is derived to adapt the CNN-based VSO process to embrace a better 3D video coding performance. Extensive experimental results show that the proposed scheme can efficiently eliminate the artifacts in the synthesized image, and reduce 25.9% and 11.7% bit rate in terms of peak-signal-to-noise ratio and structural similarity index, which significantly outperforms the state-of-the-art methods.

25 September 2024 in IEEE Transactions on Broadcasting
Verified
Journal Article
Closed access
ZGZixi Guo
Zixi Guo
Yun ZhangYun Zhang
Yun Zhang
LZLinwei Zhu
Linwei Zhu
HWHanli Wang
Hanli Wang
GJGangyi Jiang
Gangyi Jiang
Point cloud has been the mainstream representation for advanced 3D applications, such as virtual reality and augmented reality. However, the massive data amounts of point clouds is one of the most challenging issues for transmission and storage. In this paper, we propose an end-to-end voxel Transformer and Sparse Convolution based Point Cloud Attribute Compression (TSC-PCAC) for 3D broadcasting. Firstly, we present a framework of the TSC-PCAC, which includes Transformer and Sparse Convolutional Module (TSCM) based variational autoencoder and channel context module. Secondly, we propose a two-stage TSCM, where the first stage focuses on modeling local dependencies and feature representations of the point clouds, and the second stage captures global features through spatial and channel pooling encompassing larger receptive fields. This module effectively extracts global and local inter-point relevance to reduce informational redundancy. Thirdly, we design a TSCM based channel context module to exploit inter-channel correlations, which improves the predicted probability distribution of quantized latent representations and thus reduces the bitrate. Experimental results indicate that the proposed TSC-PCAC method achieves an average of 38.53%, 21.30%, and 11.19% bitrate reductions on datasets 8iVFB, Owlii, 8iVSLF, Volograms, and MVUB compared to the Sparse-PCAC, NF-PCAC, and G-PCC v23 methods, respectively. The encoding/decoding time costs are reduced 97.68%/98.78% on average compared to the Sparse-PCAC. The source code and the trained TSC-PCAC models are available at https://github.com/igizuxo/TSC-PCAC.