检索结果-内蒙古大学图书馆

2024 Conference on Visual Communications and Image Processing

作者： Zhao, Yanchen Duan, Wenhong Jia, Chuanmin Wang, Shanshe Ma, Siwei Peking Univ Sch Comp Sci Beijing Peoples R China Peking Univ Wangxuan Inst Comp Technol Beijing Peoples R China

ISBN: (纸本)9798331529543;9798331529550

In the fourth generation audio video coding standard (AVS4), the Inter Prediction Filter (INTERPF) reduces discontinuities between prediction and adjacent reconstructed pixels in inter prediction. The paper proposes a low complexity learning-based inter prediction (LLIP) method to replace the traditional INTERPF. LLIP enhances the filtering process by leveraging a lightweight neural network model, where parameters can be exported for efficient inference. Specifically, we extract pixels and coordinates utilized by the traditional INTERPF to form the training dataset. Subsequently, we export the weights and biases of the trained neural network model and implement the inference process without any third-party dependency, enabling seamless integration into video codec without relying on Libtorch, thus achieving faster inference speed. Ultimately, we replace the traditional handcraft filtering parameters in INTERPF with the learned optimal filtering parameters. This practical solution makes the combination of deep learning encoding tools with traditional video encoding schemes more efficient. Experimental results show that our approach achieves 0.01%, 0.31%, and 0.25% coding gain for the Y, U, and V components under the random access (RA) configuration on average.

关键词： video coding inter prediction learning-based complexity reduction audio video coding standard

来源：评论

学校读者我要写书评

暂无评论

Towards Next Generation video coding: from Neural Network Based Predictive coding to In-Loop Filtering 56

Towards Next Generation Video Coding: from Neural Network Ba...

引用

56th IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Zhao, Yanchen Wang, Suhong Lin, Kai Lei, Meng Jia, Chuanmin Wang, Shanshe Ma, Siwei Peking Univ Sch Comp Sci Natl Engn Res Ctr Visual Technol Beijing Peoples R China Peking Univ Wangxuan Inst Comp Technol Beijing Peoples R China

ISBN: (纸本)9781665451093

audio video coding standard (AVS) Intelligent coding Group mainly studies video coding tools based on neural network technology and its potential benefit for next generation video coding. Extensive efforts have been dedicated to the research on neural network (NN) based coding tools. In this paper, we present a novel NN based video coding framework by leveraging the supervised trained NN models for multiple modules in the hybrid coding framework, from the predictive coding to the in-loop filtering. Specifically, NN based intra prediction models the non-linear mapping from contextual pixels to the predictions. The inter prediction efficiency is enhanced by introducing a virtual reference frame (VRF) network. The convolutional neural network based loop filtering (CNNLF) with discriminative model selection exploits the texture adaptivity. The experimental results show that the CNNLF, NN Intra, and VRF models can bring 8.60%, 1.02%, and 2.26% luma BD-rate reduction under random access (RA) configuration compared with AVS reference software HPM13.0. Additional experiments with the combined three NN coding tools reveal that around 13% YUV BD-rate reduction could be obtained. The proposed framework opens novel sights for next generation video coding from the intelligent coding perspective.

关键词： video coding in-loop filter intra prediction virtual reference frame audio video coding standard

来源：评论

学校读者我要写书评

暂无评论

Equal Value String and Copy Above String Based String Prediction for SCC in AVS3

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2023年 25卷 584-592页

作者： Zhou, Kailun Zhao, Liping Ye, Zigao Wang, Huihui Lin, Tao Feng, Sheng Yang, Yufen Tongji Univ Coll Elect & Informat Engn VLSI Lab Shanghai 200092 Peoples R China Shaoxing Univ Dept Comp Sci & Engn Shaoxing 312000 Peoples R China Peking Univ Informat Technol R&D Innovat Ctr Shaoxing 312000 Peoples R China

String prediction (SP) is a very efficient screen content coding (SCC) tool which has been adopted in the third generation of audio video standard (AVS3). It is observed that two special types of strings occur frequently. To further improve the coding efficiency for SCC on top of the original SP, a new variation of SP named Equal-value-string and Copy-above-string based SP (ECSP) is proposed. An ECSP coding unit uses only three types of strings: Equal-value-string, Copy-above-string, and Unpredictable-pixel-string. Compared with the AVS3 reference software HPM9.0 with ECSP disabled, using AVS3 SCC Common Test Condition and YUV 4:2:0 test sequences, the proposed technique achieves an average Y BD-rate reduction of 5.54 and 3.01% for All Intra and Low Delay configurations, respectively, with low additional encoding and decoding complexity. The proposed ECSP has been adopted in the AVS3 standard.

关键词： audio video coding standard screen content coding string prediction equal value string 4:2:0 format

来源：评论

学校读者我要写书评

暂无评论

String Prediction for 4:2:0 Format Screen Content coding and Its Implementation in AVS3

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2021年 23卷 3867-3876页

作者： Zhou, Qingyang Zhao, Liping Zhou, Kailun Lin, Tao Wang, Huihui Wang, Shuhui Jiao, Mengcao Tongji Univ Coll Elect & Informat Engn VLSI Lab Shanghai 200092 Peoples R China Shaoxing Univ Dept Comp Sci & Engn Shaoxing 312000 Peoples R China

In the past, string prediction (also known as string matching) was applied only to RGB and YUV 4:4:4 format screen content coding. This paper proposes a string prediction approach to 4:2:0 format screen content coding implemented in the third generation of audio video standard (AVS3) in China. String prediction is applied to both YUV CU and Y CU. To further improve the coding performance, several improved technicals of string prediction are presented, including a mixed string searching strategy for finding the optimal reference string, a joint picture-level, CU-level, and pixel-level early termination strategy to reduce coding complexity, and two effective coding methods for string prediction parameters. For low-complexity hardware implementation of string prediction decoder, the memory access bandwidth is reduced by introducing string constraints. Meanwhile, string prediction reuses the reference pixel buffer of intra block copy (IBC). Compared with the newest AVS3 reference software HPM7.0 with string prediction disabled, the proposed string prediction approach achieves up to 18.48% Y BD-rate reduction. Using AVS3 Screen Content coding (SCC) Common Test Condition and YUV test sequences in Text and Graphics with Motion category, the proposed technique achieves an average Y BD-rate reduction of 10.33%, 8.47%, 6.91% for All Intra (AI), Random Access (RA) and Low Delay (LD) configurations, respectively, with low additional encoding and decoding complexity. The proposed string prediction approach has been adopted in the newest AVS3 reference software HPM7.0.

关键词： audio video coding standard screen content coding string prediction 4:2:0 format

来源：评论

学校读者我要写书评

暂无评论

video coding optimization in AVS2

引用

INFORMATION PROCESSING & MANAGEMENT 2022年第2期59卷 102808-102808页

作者： Zhou, Yimin Xu, Gencheng Tang, Kaicheng Tian, Ling Sun, Yu Chengdu Univ Informat Technol Sch Cybersecur Chengdu 610225 Peoples R China Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 611731 Peoples R China Univ Cent Arkansas Dept Comp Sci Conway AR 72035 USA

Chinese second generation of the audio video coding standard, known as the AVS2, competing with HEVC/H.265 and AV1, has become a well-known video compression standard. Many unique tools have been developed and incorporated in AVS2. This paper proposes several encoder optimization schemes with respect to rate-distortion optimization (RDO). Specifically, by exploiting the close relationship between the total number of referenced pictures and the hierarchy of reference structure, a reference structure determined parameter (RSDP) algorithm reallocates Lagrange multiplier. Moreover, an adaptive quantization parameter offset (AQPO) algorithm is provided at both picture-level and Groups of Pictures (GoP)-level to adjust quantization parameters adaptively on top of the preassigned ones. Both RSDP algorithm and AQPO algorithm have already been adopted by AVS2 and incorporated in its reference software. Experimental results show that in the low-delay, RSDP and AQPO achieved savings of 1.35% and 1.26% on BDBR, respectively.

关键词： audio video coding standard Rate-distortion optimization Optimization problem Hierarchical reference structure Bit-rate reallocation

来源：评论

学校读者我要写书评

暂无评论

A String Prediction-Based Algorithm to AVS3 Screen Content coding 20

A String Prediction-Based Algorithm to AVS3 Screen Content C...

引用

Proceedings of the 2020 4th International Conference on video and Image Processing

作者： Dong Jiang zhu hong Cheng Fang Feiyang Zeng Jucai Lin Jun Yin Zhejiang Dahua Technology Co.Ltd China Zhejiang Dahua Technology Co.Ltd Hangzhou China

ISBN: (纸本)9781450389075

String Prediction (SP) is a special intra prediction mode for screen content coding, which can provide better coding efficiency while keeping lower coding complexity. In this paper, we present a string prediction-based improved algorithm to third-generation of the audio video coding standard (AVS3) screen content coding (SCC). The main content is to use the string vector (SV) of history-based block vector prediction (HBVP) as string vector prediction (SVP), and obtain the best SV by comparing the rate-distortion (RD) cost, which comes from CU-level estimation search and pixel-level motion estimation search. SV is equal to the sum of SVP and string vector difference (SVD). While the encoder only needs to signal the SVD and the HBVP index to the decoder. The experiments show that with little coding complexity increases, the algorithm presented in this paper achieves an average Y BD-rate of -5.02% (TGM)/ -3.06% (MC), U BD-rate of -5.10% (TGM)/ -3.39% (MC), V BD-rate of -5.08% (TGM)/ -3.66% (MC) from AVS SCC common test condition (CTC) test suite in all intra configuration.

关键词： audio video coding standard String Prediction Screen Content coding

来源：评论

学校读者我要写书评

暂无评论

A Split-Based Algorithm Optimization for AVS3 Intra coding 2020

A Split-Based Algorithm Optimization for AVS3 Intra Coding

引用

2020 4th International Conference on Computer Science and Artificial Intelligence

作者： XUE ZHANG DONG JIANG ZHU HONG FEIYANG ZENG JUCAI LIN JUN YIN R&D center Zhejiang Dahua Technology Co.Ltd China

ISBN: (纸本)9781450388436

IntraDT is an intra coding algorithm in AVS3, which is used to further divide the current coding block to obtain multiple sub blocks for prediction. The optimal prediction modes in each sub block are selected adaptively. In this paper, we propose a split-based intra coding algorithm based on the intraDT algorithm of AVS3, which makes the partition of sub blocks match the image texture more accurately. The improvement of the proposed method mainly lies in the addition of vertical and horizontal symmetric binary partition mode, and the specified transform partition modes corresponding to the two prediction partition modes, compared with intraDT. The optional prediction partition modes are extended, and the transform partition modes under the new partition modes are not necessary to be transmitted. The new partition modes can match the image texture more accurately, and find a better balance between the depth of CU partition and the redundancy of prediction block partition. The experimental results show that the proposed method is effective for the test sequences in common test condition in AVS3. The BD-rate for the components of Y, U and V achieve gains of 0.13%, 0.44% and 0.32% under All-Intra configuration, respectively, while achieving gains of 0.12%, 0.02% and 0.26% under Random-Access configuration.

关键词： audio video coding standard Intra coding Partition

来源：评论

学校读者我要写书评

暂无评论

Residual in Residual Based Convolutional Neural Network In-loop Filter for AVS3

Residual in Residual Based Convolutional Neural Network In-l...

引用

Picture coding Symposium (PCS)

作者： Lin, Kai Jia, Chuanmin Zhao, Zhenghui Wang, Li Wang, Shanshe Ma, Siwei Gao, Wen Peking Univ Inst Digital Media Beijing Peoples R China Hikvis Res Inst Hangzhou Peoples R China

ISBN: (纸本)9781728147048

Deep learning based video coding tools development has been an emerging topic recently. In this paper, we propose a novel deep convolutional neural network (CNN) based in-loop filter algorithm for the third generation of audio video coding standard (AVS3). Specifically, we first introduce a residual block based CNN model with global identity connection for the luminance in-loop filter to replace conventional rule-based algorithms in AVS3. Subsequently, the reconstructed luminance channel is deployed as textural and structural guidance for chrominance filtering. The corresponding syntax elements are also designed for the CNN based in-loop filtering. In addition, we build a large scale database for the learning based in-loop filtering algorithm. Experimental results show that our method achieves on average 7.5%, 16.9% and 18.6% BD-rate reduction under all intra (AI) configuration on common test sequences. In particular, the performance for 4K videos is 6.4%, 15.5% and 17.5% respectively. Moreover, under random access (RA) configuration, the proposed method brings 3.3%, 14.4%, and 13.6% BD-rate reduction separately.

关键词： video coding In-loop Filter audio video coding standard Convolution Neural Network

来源：评论

学校读者我要写书评

暂无评论

CWT and CS Algorithm Based video Watermarking using audio Watermark 4

CWT and CS Algorithm Based Video Watermarking using Audio Wa...

引用

4th International Conference on Recent Trends in Computer Science and Engineering (ICRTCSE)

作者： Sundararajan, M. Yamuna, G. Annamalai Univ Dept Elect Engn Annamalainagar 608002 Tamil Nadu India

To increase the robustness of the scheme, we have developed an efficient video watermarking scheme to embed audio watermark based on optimal location. Before embed the audio watermark in to the digital video, the input video sequence is segmented into shots using discrete cosine transform. The segmented video shots are partitioned addicted to number of frames for the embedding process. In this process the PSNR value calculated for each frames and select the best frame by using CS algorithm. The audio data is utilized as a watermark to embed into the digital video sequence. Initially, the audio data is converted into 9 bit sequence and then it is encrypted. In watermarking embedding process, segmented video data is given to the Coiflets wavelet transform and the encrypted audio watermark data is embedded based on optimal location analysis that is carried out using CS algorithm. Later, the original audio data is extracted from the watermarked video using the designed watermarking extraction procedure. The performance of video watermarking is analyzed in terms of various attacks. (C) 2016 The Authors. Published by Elsevier B.V.

关键词： video watermarking 9-bit conversion audio video coding standard Embedding Extraction

来源：评论

学校读者我要写书评

暂无评论

CWT and CS Algorithm Based video Watermarking Using audio Watermark

引用

Procedia Computer Science 2016年 87卷 93-98页

作者： M. Sundararajan G. Yamuna Assistant professor Department of Electrical Engineering Annamalai University Annamalai Nagar 608002 India Professor Department of Electrical Engineering Annamalai University Annamalai Nagar 608002 India

关键词： video watermarking 9-bit conversion audio video coding standard Embedding Extraction

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：