检索结果-内蒙古大学图书馆

SR-LBSCC: Super resolution based screen content image compression at low bitrate

PATTERN RECOGNITION LETTERS 2025年 191卷 96-102页

作者： Tang, Tong Li, Min Zhang, Xin Zheng, Shenhai Li, Weisheng Chongqing Univ Posts & Telecommun Sch Comp Sci & Technol Chongwen Rd 2 Chongqing 400065 Peoples R China Key Lab Image Cognit Chongwen Rd 2 Chongqing 400065 Peoples R China Chongqing Univ Posts & Telecommun Sch Commun & Informat Engn Chongwen Rd 2 Chongqing 400065 Peoples R China

The massive amount of screen content data puts enormous pressure on storage and bandwidth, and traditional screen content encoding methods (e.g. HEVC-SCC) cannot meet the requirements of high efficient compression. The main challenge is how to retain the sharp edges when screen content images are encoded with low bitrates. In this paper, we propose a super resolution (SR) based screen content image compression method for low bitrate encoding (SR-LBSCC). Concretely, first, the original image is down-sampled and compressed with the traditional screen content coding method, which significantly reduces the encoded bitrate. Then, a novel SR neural network is designed to enhance quality of reconstructed image, which could recover details and remove compression artifacts. Finally, experimental results show that compared with the standard HEVC-SCC, the proposed method could averagely reduce bitrate cost by 17.02% and 24.97% respectively on the SCID and SIQAD datasets at similar subjective quality.

关键词： screen content coding Super resolution Image compression High efficiency video coding (HEVC)

来源：评论

学校读者我要写书评

暂无评论

Hardware-Decoder-Friendly High Throughput String Prediction for SCC Implemented in AVS3

引用

IEEE SIGNAL PROCESSING LETTERS 2025年 32卷 1166-1170页

作者： Zhao, Liping Yan, Zhuge Wu, Zongda Wang, Jiangda Lin, Tao Shaoxing Univ Dept Comp Sci & Engn Shaoxing 312000 Peoples R China Shaoxing Univ Inst Artificial Intelligence Shaoxing 312000 Peoples R China Peking Univ Informat Technol R&D Innovat Ctr Shaoxing 312000 Peoples R China Tongji Univ VLSI Inst Shanghai 200092 Peoples R China

String prediction (SP) is a highly efficient screen content coding technique adopted into international and China video coding standards. However, SP requires a high number of SRAM fetches to decode and output a block for display, leading to low throughput (T). Low T results in a high decoder and SRAM clock frequency to output the required number of display pixels, which is determined by the specific display resolution and frame rate. To achieve hardware-decoder-friendly high throughput SP (HTSP), this paper exploits specific SRAM fetch rate constraints for five SRAM-cell sizes commonly used in hardware decoder designs. Additionally, the optimal reference string selection process is formulated as a multi-constraint rate-distortion optimization (MCRDO) problem and a novel reference string searching method is presented. HTSP boosts throughput by up to 4 times compared to the state-of-the- art SP, with only a negligible impact on coding efficiency.

关键词： Video coding screen content coding screen content coding audio video standard audio video standard string prediction string prediction SRAM SRAM high throughput high throughput

来源：评论

学校读者我要写书评

暂无评论

A Character Position-Aware Compression Framework for screen Text Image

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2024年第9期34卷 8821-8835页

作者： Zhu, Chen Lu, Guo Chen, Huanbang Feng, Donghui Wang, Shen Zhao, Yan Xie, Rong Song, Li Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Shanghai 200240 Peoples R China Huawei Technol Co Ltd Shenzhen 518129 Peoples R China Shanghai Jiao Tong Univ AI Inst MoE Key Lab Artificial Intelligence Shanghai 200240 Peoples R China

Text patterns typically exhibit distinct boundaries and sparse color histograms. However, in current hybrid codec frameworks, the positions of coding units are often misaligned with the text patterns, resulting in prediction and color mapping tools consuming a large number of bits to indicate these patterns. Nowadays, some text detection and recognition methods have been proposed to accurately locate and analyze the text regions in screen images. Combined with these techniques, we propose a character position-aware compression framework for screen text image. On the encoder side, a low-complexity detection method is adopted to locate the text characters. Then it copies the detected characters to the position aligned with the coding unit (CU) grid to form a text layer. This text-layer representation can further increase the efficiency of existing screen content coding tools such as Intra Block Copy (IBC). Moreover, we design several compression tools based on this representation. We extend the two Motion Vector (MV) prediction modes: Adaptive Motion Vector Prediction (AMVP) and Merge. We modify the MV encoding syntax according to the layout characteristics of the text layer. We present a Gradient-guided In-loop Filter (GIF) to sharpen the text lines using a convolutional network. Experiments conducted on VVC reference software VTM all_intra configuration show that the proposed framework can achieve an average bitrate savings of 4.6% and 3.6% under the w/GIF and w/o GIF versions, with a corresponding increase in CPU encoding complexity of 72% and 10%.

关键词： screen content coding text detection motion vector prediction and coding in-loop filter

来源：评论

学校读者我要写书评

暂无评论

Spatial-temporal feature guided adaptive rate control for screen content videos

引用

JOURNAL OF REAL-TIME IMAGE PROCESSING 2024年第6期21卷 183页

作者： Lin, Qi Chen, Jing Huaqiao Univ Coll Informat Sci & Engn Xiamen 361021 Peoples R China

In this paper, an adaptive rate control algorithm based on screen content characteristics is proposed. It enhances the coding performance of HEVC Extensions on screen content coding (HEVC-SCC) by leveraging the unique characteristics of screen content videos (SCVs). Firstly, considering the characteristics of the human visual system (HVS) and the particular spatial-temporal characteristics of SCVs, the spatial feature (SF) and temporal feature (TF) factors are extracted by Gabor filter. Then, a spatial-temporal fused feature of SVC is modeled an adaptive R-lambda\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$R-\lambda$$\end{document} model to guide the rate control of HEVC-SCC. More bitrates are allocated to coding tree units (CTUs) that have higher vision sensitivity, and vice versa. The experimental results demonstrate the effectiveness of the proposed STF_RC. It achieves a quality improvement of 1.70 dB in Low Delay B (LDB) and 2.55 dB in Random Access (RA) configurations. Additionally, it reduces bitrate by 21.75% in LDB and 25.42% in RA compared to the standard platform. Compared to state-of-the-art rate control algorithms for HEVC-SCC, it reduces bitrate mismatch significantly and achieves better performance in both rate-distortion and subjective quality.

关键词： screen content coding Spatial-temporal feature Rate control HEVC-SCC

来源：评论

学校读者我要写书评

暂无评论

A memory access number constraint-based string prediction technique for high throughput SCC implemented in AVS3

引用

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 2024年 105卷

作者： Zhao, Liping Yan, Zuge Hu, Keli Feng, Sheng Wang, Jiangda Cao, Xueyan Lin, Tao Shaoxing Univ Dept Comp Sci & Engn Shaoxing Peoples R China Tongji Univ Coll Elect & Informat Engn Shanghai Peoples R China Peking Univ Informat Technol R&D Innovat Ctr Beijing Peoples R China Shaoxing Univ Inst Artificial Intelligence Shaoxing Peoples R China Zhejiang Prov Peoples Hosp Canc Ctr Dept Gastroenterol Hangzhou Peoples R China

String prediction (SP) is a highly efficient screen content coding (SCC) tool that has been adopted in international and Chinese video coding standards. SP exhibits a highly flexible and efficient ability to predict repetitive matching patterns. However, SP also suffers from low throughput of decoded display output pixels per memory access, which is synchronized with the decoder clock, due to the high number of memory accesses required to decode an SP coding unit for display. Even in state-of-the-art (SOTA) SP, the worst-case scenario involves two memory accesses for decoding each 4-pixel basic string unit across two memory access units, resulting in a throughput as low as two pixels per memory access (PPMA). To solve this problem, we are the first to propose a technique called memory access number constraint-based string prediction (MANC-SP) to achieve high throughput in SCC. First, a novel MANC-SP framework is proposed, a well-designed memory access number constraint rule is established on the basis of statistical data, and a constrained RDO-based string searching method is presented. Compared with the existing SOTA SP, the experimental results demonstrate that MANC-SP can improve the throughput from 2 to 2.67 PPMA, achieving a throughput improvement of 33.33% while maintaining a negligible impact on coding efficiency and complexity.

关键词： Video coding screen content coding Audio video standard String prediction High throughput

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

Compressing of Medium- to Low-Rate Transform Residuals With Semi-Extreme Sparse coding as an Alternate Transform in Video coding

引用

IEEE TRANSACTIONS ON CONSUMER ELECTRONICS 2023年第3期69卷 271-286页

作者： Schimpf, Michael G. Lign, Nam Liu, Ying Santa Clara Univ Dept Comp Sci & Engn Santa Clara CA 95050 USA

Modern hybrid video codecs split their video content into blocks. These blocks are predicted and the difference between original and predicted block is calculated. This residual block is transformed by a discrete cosine transform (DCT) from the pixel domain into the frequency domain and quantized by a dead-zone quantizer (DZQ), which removes high frequency signals, depending on the quantization parameter (QP). DZQ has an extended zone around zero, which acts as a noise-gate, removing noise as intended but also removing useful signals. DCT and DZQ are not the optimal solution, they create distortions and side effects at lower bitrates. In contrast, sparse coding does not have these problems at lower bitrates, but it compresses inefficient at higher bit rates. We propose a method to add sparse coding as an alternate transform, which is controlled by a rate-distortion optimization (RDO) decision, in a semi-extreme sparse coding (SESC) setup and uses a semi-extreme dictionary training (SEDT) process. It is integrated into the High Efficiency Video coding (HEVC) test model HM-16.18 and screen content coding (HEVC-SCC) test model HM-16.18+SCM-8.7. Experimental results demonstrate that the proposed method achieves a Bjontegaard rate difference (BD-rate) of up to 5.5% compared to the standard.

关键词： Video coding sparse coding sparse representation orthogonal matching pursuit screen content coding HEVC residual coding intra prediction KSVD

来源：评论

学校读者我要写书评

暂无评论

LOW-COMPLEXITY DICTIONARY BASED LOSSLESS screen content coding

LOW-COMPLEXITY DICTIONARY BASED LOSSLESS SCREEN CONTENT CODI...

引用

IEEE International Conference on Image Processing

作者： Meng Xu Zhan Ma Wei Wang Xian Wang Haoping Yu Huawei USA R&D Center Santa Clara CA USA

ISBN: (纸本)9781479957521

This paper presents a low-complexity lossless screen content coding method on top of a well structured dictionary based solution DictSCC. Both methods are implemented on the emerging High-Efficiency Video coding (HEVC) Range Extensions (RExt) to demonstrate the coding efficiency. Compared with the DictSCC our scheme further explores the 2D correlation between neighboring image blocks for performance improvement, and reduces the complexity significantly by constraining the dictionary buffer which will be more favored by the hardware implementation. Results demonstrate averaged 17%, 10% and 8% bit rate reduction over HEVC for screen content compression with respect to All Intra, Random Access and Low-Delay encoder configurations.

关键词： video coding DictSCC HEVC RExt high-efficiency video coding range extensions lossless screen content coding low-complexity dictionary Artificial intelligence Bit rate Complexity theory Dictionaries Encoding Image color analysis Video coding HEVC dictionary coding screen content coding Video coding Dictionaries as Topic image colour analysis Bit rate Complexity theory High efficiency video coding Artificial Intelligence Lossless coding bit rate reduction screen

来源：评论

学校读者我要写书评

暂无评论

ADAPTING LEARNED IMAGE CODECS TO screen content VIA ADJUSTABLE TRANSFORMATIONS 31

ADAPTING LEARNED IMAGE CODECS TO SCREEN CONTENT VIA ADJUSTAB...

引用

2024 International Conference on Image Processing

作者： Dogaroglu, H. Burak Koyuncu, A. Burakhan Boev, Atanas Alshina, Elena Steinbach, Eckehard Tech Univ Munich Sch Computat Informat & Technol Munich Germany Huawei Munich Res Ctr Munich Germany Munich Inst Robot & Machine Intelligence Munich Germany

ISBN: (纸本)9798350349405;9798350349399

As learned image codecs (LICs) become more prevalent, their low coding efficiency for out-of-distribution data becomes a bottleneck for some applications. To improve the performance of LICs for screen content (SC) images without breaking backwards compatibility, we propose to introduce parameterized and invertible linear transformations into the coding pipeline without changing the underlying baseline codec's operation flow. We design two neural networks to act as prefilters and postfilters in our setup to increase the coding efficiency and help with the recovery from coding artifacts. Our end-to-end trained solution achieves up to 10% bitrate savings on SC compression compared to the baseline LICs while introducing only 1% extra parameters.

关键词： screen content coding learned image compression prefilter postfilter deep learning

来源：评论

学校读者我要写书评

暂无评论

Independent Uniform Prediction Mode for screen content Video coding

Independent Uniform Prediction Mode for Screen Content Video...

引用

IEEE Visual Communications and Image Processing Conference

作者： Zhang, Xingyu Cohen, Robert A. Vetro, Anthony Hong Kong Univ Sci & Technol Kowloon Hong Kong Peoples R China Mitsubishi Elect Res Labs Cambridge MA 02139 USA

ISBN: (纸本)9781479961399

Many of the existing video coding standards in use today were developed primarily using camera-captured content as test material. Today, with the more widespread use of connected devices, there is an increased interest in developing video coding tools that target screen content video. screen content video is often characterized by having sharp edges, noiseless graphics-generated region, repeated patterns, limited sets of colors, etc. This paper presents an independent uniform prediction (IUP) mode for improving the coding efficiency of screen content video. IUP chooses one color out of a small set of global colors to form a uniform prediction block. Unlike existing palette-based modes, IUP does not have to construct and signal a color index map for every block that is coded. Experimental results using IUP in the HEVC Range Extensions 6.0 framework are presented, along with results using techniques that reduce complexity so that the IUP-based encoder is faster than the reference encoder.

关键词： screen content coding HEVC prediction modes independent uniform prediction

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：