检索结果-内蒙古大学图书馆

Perceptual Quality-Oriented Rate Allocation via Distillation from End-to-End Image Compression

ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 2024年第7期20卷 1–22页

作者： Yang, Runyu Liu, Dong Ma, Siwei Wu, Feng Gao, Wen Univ Sci & Technol China 443 Huangshan Rd Hefei 230027 Anhui Peoples R China Peking Univ 5 Yiheyuan Rd Beijing 100871 Peoples R China Peng Cheng Lab 2 Xingkeyi St Shenzhen 518055 Peoples R China

Mainstream image/video coding standards, exemplified by the state-of-the-art H.266/VVC, AVS3, and AV1, follow the block-based hybrid coding framework. Due to the block-based framework, encoders designed for these standards are easily optimized for peak signal-to-noise ratio (PSNR) but have difficulties optimizing for the metrics more aligned to perceptual quality, e.g., multi-scale structural similarity (MS-SSIM), since these metrics cannot be accurately evaluated at the small block level. We address this problem by leveraging inspiration from the end-to-end image compression built on deep networks, which is easily optimized through network training for any metric as long as the metric is differentiable. We compared the trained models using the same network structure but different metrics and observed that the models allocate rates in different ratios. We then propose a distillation method to obtain the rate allocation rule from end-to-end image compression models with different metrics and to utilize such a rule in the block-based encoders. We implement the proposedmethod on the VVC reference software-VTMand the AVS3 reference software-HPM, focusing on intraframe coding. Experimental results show that the proposed method on top of VTM achieves more than 10% BD-rate reduction than the anchor when evaluated withMS-SSIM or LPIPS, which leads to concrete perceptual quality improvement.

关键词： AVS3 block-based coding end-to-end image compression H.266/VVC perceptual quality rate allocation

来源：评论

学校读者我要写书评

暂无评论

Adaptive deblocking filter

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2003年第7期13卷 614-619页

作者： List, P Joch, A Lainema, J Bjontegaard, G Karczewicz, M Deutsch Telekom T Syst D-64295 Darmstadt Germany UB Video Inc Vancouver BC V6B 2R9 Canada Nokia Res Ctr Irving TX 75039 USA TANDBERG N-1324 Lysaker Norway

This paper describes the adaptive deblocking filter used in the H.264/MPEG-4 AVC video coding standard. The filter performs simple operations to detect. and analyze artifacts on coded block boundaries and. attenuates ... 详细信息

关键词： block-based coding video coding video filtering video signal processing

来源：评论

学校读者我要写书评

暂无评论

DCT information recovery of erroneous image blocks by a neural predictor

引用

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 2000年第6期18卷 1111-1121页

作者： De Natale, FGB Perra, C Vernazza, G Univ Trent DICA I-38050 Trent Italy Univ Cagliari DIEE I-09123 Cagliari Italy Univ Genoa DIBE I-16145 Genoa Italy

In this paper, the problem of DCT information recovery in the transmission of coded visual data over packet networks is addressed. The loss of a packet conveying coded block data leads to the unsuccessful reconstruction of the relevant area, with consequent degradation of the received image quality. The proposed method allows recovery of a subset of the missing DCT coefficients sufficient to achieve good reconstruction quality of the lost block, based on the available surrounding information. To this purpose, a neural predictor was carefully designed and suitably trained with an appropriate set of synthetic and natural patterns. An extensive testing phase, performed on a large set of images with different frequency characteristics, revealed that the method provides very good reconstruction capabilities.

关键词： block-based coding error concealment neural prediction

来源：评论

学校读者我要写书评

暂无评论

HEVC Deblocking Filter

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2012年第12期22卷 1746-1754页

作者： Norkin, Andrey Bjontegaard, Gisle Fuldseth, Arild Narroschke, Matthias Ikeda, Masaru Andersson, Kenneth Zhou, Minhua Van der Auwera, Geert Ericsson Res S-16489 Stockholm Sweden Cisco Syst Norway N-1366 Lysaker Norway Panason Res & Dev Ctr D-63255 Langen Germany Sony Corp Technol Dev Grp Tokyo 1418610 Japan Texas Instruments Inc Syst & Applicat Res & Dev Ctr Dallas TX 75243 USA Qualcomm Technol Inc San Diego CA 92121 USA

This paper describes the in-loop deblocking filter used in the upcoming High Efficiency Video coding (HEVC) standard to reduce visible artifacts at block boundaries. The deblocking filter performs detection of the artifacts at the coded block boundaries and attenuates them by applying a selected filter. Compared to the H.264/AVC deblocking filter, the HEVC deblocking filter has lower computational complexity and better parallel processing capabilities while still achieving significant reduction of the visual artifacts.

关键词： block-based coding deblocking video coding video filtering video processing

来源：评论

学校读者我要写书评

暂无评论

SHAPE-ADAPTIVE DCT FOR GENERIC coding OF VIDEO

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 1995年第1期5卷 59-62页

作者： SIKORA, T MAKAI, B Department of Digital Image Processing Heinrich-Hertz Institute for Communications Engineering Berlin Germany

In this paper, a low complexity shape-adaptive DCT algorithm suitable for coding pels in arbitrarily shaped image segments is introduced. In contrast to other techniques described in literature the proposed algorithm is based on predefined orthogonal sets of DCT basis functions and does not require more computations than a normal block DCT. It is shown that the shape-adaptive DCT algorithm can be easily incorporated into existing block-based JPEG, H.261, or MPEG coding schemes. Thus segment or object based coding of images and video can be provided with backward compatibility to existing coding standards. As an important feature, with the proposed technique additional content based functionalities currently discussed in the MPEG-4 standardization phase can be readily achieved.

关键词： discrete cosine transforms image segmentation video coding DCT basis functions H.261 JPEG MPEG coding MPEG-4 standardization backward compatibility block-based coding coding standards image segments shape-adaptive DCT algorithm Video coding JPEG code standards discrete cosine transforms image segmentation Videotapes backward compatibility

来源：评论

学校读者我要写书评

暂无评论

Design of wavelet-based image codec in memory-constrained environment

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2001年第5期11卷 642-650页

作者： Bao, YL Kuo, CCY Univ So Calif Integrated Multimedia Syst Ctr Los Angeles CA 90089 USA Univ So Calif Dept Elect Engn Syst Los Angeles CA 90089 USA

This work presents a high-performance wavelet transform based image coder that is designed for image compression in a system with limited resources. In this image coder the dual-sliding wavelet transform (DSWT) is first applied to image data to generate wavelet coefficients in fixed-size blocks. Here, a block consists of wavelet coefficients only from a single subband. Then, the resulting coefficient blocks are directly coded with the Low-Complexity Binary Description (LCBiD) coefficient coding algorithm. No parent-child relationship is exploited in the coding process. There is no intermediate buffering needed between DSWT and LCBiD. The compressed bit stream generated by the proposed coder is both SNR and resolution scalable, as well as highly resilient to transmission errors. Both DSWT and LCBiD process the data in blocks whose size is independent of the size of the input image. This gives more flexibility in its implementation. The codec has a very good coding performance even the size of a coefficient block is as small as (16,16).

关键词： block-based coding block-based transform image compression low complexity compression wavelet transform

来源：评论

学校读者我要写书评

暂无评论

Accessible Computer Science for K-12 Students with Hearing Impairments 14th

Accessible Computer Science for K-12 Students with Hearing I...

引用

14th International Conference on Universal Access in Human-Computer Interaction (UAHCI) part of the 22nd International Conference on Human-Computer Interaction (HCI)

作者： Das, Meenakshi Marghitu, Daniela Jamshidi, Fatemeh Mandala, Mahender Howard, Ayanna Auburn Univ Auburn AL 36830 USA Georgia Inst Technol Atlanta GA 30332 USA

ISBN: (纸本)9783030491079;9783030491086

An inclusive science, technology, engineering and mathematics (STEM) workforce is needed to maintain America's leadership in the scientific enterprise. Increasing the participation of underrepresented groups in STEM, including persons with disabilities, requires national attention to fully engage the nation's citizens in transforming its STEM enterprise. To address this need, a number of initiatives, such as AccessCSforALL, Bootstrap, and CSforAll, are making efforts to make Computer Science inclusive to the 7.4 million K-12 students with disabilities in the U.S. Of special interest to our project are those K-12 students with hearing impairments. American Sign Language (ASL) is the primary means of communication for an estimated 500,000 people in the United States, yet there are limited online resources providing Computer Science instruction in ASL. This paper introduces a new project designed to support Deaf/Hard of Hearing (D/HH) K-12 students and sign interpreters in acquiring knowledge of complex Computer Science concepts. We discuss the motivation for the project and an early design of the accessible block-based Computer Science curriculum to engage D/HH students in hands-on computing education.

关键词： Accessibility American Sign Language block-based coding

来源：评论

学校读者我要写书评

暂无评论

An analysis of memory bandwidth requirements for the H.263 video codec

An analysis of memory bandwidth requirements for the H.263 v...

引用

Visual Communications and Image Processing 1998 Conference

作者： Kapoor, B Texas Instruments Inc DSPS R&D Ctr Dallas TX 75243 USA

ISBN: (纸本)0819427497

Memory bandwidth is emerging as the fundamental impediment to higher performance and lower power computer and communication systems. In this paper, we present an analysis of memory bandwidth requirements for the H.263 video codec algorithms. We provide data and insight into how the choice of cache parameters affects external bandwidth requirements of video. We make use of memory traces generated as a result of running Telenor's H.263 video encoder and decoder software implementations to simulate a large number of cache configurations. In the area of analysis of video algorithms, this paper focuses on the following issues: We provide a study of how varying cache size, block size, associativity, replacement policy, and organization parameters such as split versus unified cache affects memory bandwidth requirements. A comparative study of encoder and decoder bandwidth requirements is presented. We also study various advanced encoding options provided with the H.263 standard in this light. based on our study, we provide guidelines for traffic-directed memory system design.

关键词： memory bandwidth cache H.263 low bit-rate video coding block-based coding video encoding video decoding

来源：评论

学校读者我要写书评

暂无评论

Revisiting Analogical Reasoning in Computing Education: Use of Similarities Between Robot Programming Tasks in Debugging

引用

JOURNAL OF EDUCATIONAL COMPUTING RESEARCH 2023年第5期61卷 1036-1063页

作者： Kim, ChanMin Dinc, Emre Lee, Eunseo Baabdullah, Afaf Zhang, Anna Y. Belland, Brian R. Penn State Univ University Pk PA USA

Analogical reasoning is considered to be a critical cognitive skill in programming. However, it has been rarely studied in a block-based programming context, especially involving both virtual and physical objects. In this multi-case study, we examined how novice programming learners majoring in early childhood education used analogical reasoning while debugging block code to make a robot perform properly. Screen recordings, scaffolding entries, reflections, and block code were analyzed. The cross-case analysis suggested multimodal objects enabled the novice programming learners to identify and use structural relations. The use of a robot eased the verification process by enabling them to test their analogies immediately after the analogy application. Noticing similar functional analogies led to noticing similarities in the relation between block code as well as between block code and the robot, guiding to locate bugs. Implications and directions for future educational computing research are discussed.

关键词： computing education robot programming and debugging analogical reasoning novice programming learners block-based coding

来源：评论

学校读者我要写书评

暂无评论

HEVC deblocking filtering and decisions

HEVC deblocking filtering and decisions

引用

Conference on Applications of Digital Image Processing XXXV

作者： Norkin, Andrey Andersson, Kenneth Fuldseth, Arild Bjontegaard, Gisle Ericsson Res Stockholm Sweden Cisco Syst Oslo Norway

ISBN: (纸本)9780819492166

The emerging High Efficiency Video coding (HEVC) standard uses a block-based coding scheme, which may cause blocking artifacts, especially at lower bitrates. An adaptive in-loop deblocking filter is used in the standard to reduce visible artifacts at block boundaries. The deblocking filter detects artifacts at the block boundaries and attenuates them by applying a selected filter. This paper will present deblocking decisions and filtering operations that are used in HEVC.

关键词： deblocking video coding video processing block-based coding filtering

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：