检索结果-内蒙古大学图书馆

Data Compression Conference (DCC)

作者： Itsuki Kobayashi Seishi Takamura Faculty of Computer and Information Sciences Hosei University Tokyo Japan

ISBN: (数字)9798331534714

ISBN: (纸本)9798331534721

Imaging devices capable of capturing multiple modalities, such as visible light, depth, and infrared, are increasingly prevalent, necessitating efficient compression methods. Previous research independently compressed depth, infrared, and visible information. In contrast, this study aims to improve the coding efficiency of grayscale images by utilizing infrared images as auxiliary data. This approach employs 20 encoding methods, including 19 prediction methods integrating infrared images. We assume that both the encoder and decoder already have a common infrared image before encoding the grayscale image.

关键词： image coding Imaging Data compression Prediction methods Gray-scale Decoding

来源：评论

学校读者我要写书评

暂无评论

Three-Stage Progressive Pre-Analysis Framework for VMAF Controllable image coding

Three-Stage Progressive Pre-Analysis Framework for VMAF Cont...

引用

Data Compression Conference (DCC)

作者： Shaokang Wang Guoqing Xiang Wenzhao Li Mingyuan Yang Fan Yang Shanghang Zhang Xiaodong Xie Huizhu Jia School of Computer Science Peking University Beijing China Alibaba Cloud Computing Beijing China

ISBN: (数字)9798331534714

ISBN: (纸本)9798331534721

To achieve controllable subjective quality in image coding, this paper proposes a Video Multi-method Assessment Fusion (VMAF)-oriented image coding pre-analysis algorithm, enabling the adaptive derivation of quantization parameters corresponding to a specified quality target. First, a $Q-\mathcal{V}$ model is constructed to describe the relationship between encoding quantization and VMAF distortion. Then, a Three-stage Progressive Control (TPC) algorithm, shown in Fig. 1(a), is designed to adapt quantization parameters using the discovered $Q-\mathcal{V}$ model. The first two stages, based on lightweight feature extraction, iteratively fit the distortion metrics intrinsically calculated by VMAF to predict the VMAF value for a given sample under specified distortion conditions. The final stage fits the $Q-\mathcal{V}$ model parameters using multi-point VMAF distortion data and outputs the corresponding quantization step for encoder control. A two-pass refinement algorithm, depicted in Fig. 1(b), further adjusts the quantization parameters based on the first encoding pass, improving quality control accuracy and framework robustness. Experiments on four datasets show that the quality control error remains below 1.293% for various VMAF targets, and the two-pass refinement reduces it further to 0.710%, outperforming existing methods.

关键词： Measurement Adaptation models Quantization (signal) image coding Quality control Distortion Prediction algorithms Feature extraction Encoding Robustness

来源：评论

学校读者我要写书评

暂无评论

Semantic Prior-Guided Scalable image coding

Semantic Prior-Guided Scalable Image Coding

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Wuzhen Shi Wennan Yin Fei Tao Yang Wen Guangdong Province Engineering Laboratory for Digital Creative Technology College of Electronics and Information Engineering Shenzhen University Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

We propose a semantic priori-guided scalable image coding method for simultaneously supporting fast machine vision analysis and high quality human visual experience. To obtain high-performance machine vision analysis results with a more compact base layer bitrate, our base layer directly encodes intermediate semantic features of the pre-trained machine vision task network, which effectively reduces the impact of the information needed for the human vision task. To improve model performance while quickly supporting machine vision tasks, we use structural re-parameterization technology to optimize the model. Considering that the base layer’s semantic features can effectively reflect the regions of important image content, we use the semantic prior provided by the base layer to guide the enhancement layer encoding and decoding, which allows us to pay more attention to the reconstruction of semantically important regions. In addition, we use the base layer features to predict the enhancement layer features for performing feature-domain residual coding, which further reduces the bitrate and also reduces the effect of noise compared to pixel-domain residual coding. Extensive experimental results show that our method achieves significant advantages in both object detection performance and image reconstruction tasks compared with BPG and state-of-the-art deep learning-based scalable image coding methods.

关键词： Deep learning Visualization image coding Machine vision Semantics Bit rate Noise Object detection Speech processing image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Tell Codec What Worth Compressing: Semantically Disentangled image coding for Machine with LMMs

arXiv

引用

arXiv 2024年

作者： Liu, Jinming Wei, Yuntao Lin, Junyan Zhao, Shengyang Sun, Heming Chen, Zhibo Zeng, Wenjun Jin, Xin Shanghai Jiao Tong University China Ningbo Institute of Digital Twin Eastern Institute of Technology Ningbo China University of Science and Technology of China China Yokohama National University Japan

We present a new image compression paradigm to achieve "intelligently coding for machine" by cleverly leveraging the common sense of Large Multimodal Models (LMMs). We are motivated by the evidence that large language/multimodal models are powerful general-purpose semantics predictors for understanding the real world. Different from traditional image compression typically optimized for human eyes, the image coding for machines (ICM) framework we focus on requires the compressed bitstream to more comply with different downstream intelligent analysis tasks. To this end, we employ LMM to tell codec what to compress: 1) first utilize the powerful semantic understanding capability of LMMs w.r.t object grounding, identification, and importance ranking via prompts, to disentangle image content before compression, 2) and then based on these semantic priors we accordingly encode and transmit objects of the image in order with a structured bitstream. In this way, diverse vision benchmarks including image classification, object detection, instance segmentation, etc., can be well supported with such a semantically structured bitstream. We dub our method "SDComp" for "Semantically Disentangled Compression", and compare it with state-of-the-art codecs on a wide variety of different vision tasks. SDComp codec leads to more flexible reconstruction results, promised decoded visual quality, and a more generic/satisfactory intelligent task-supporting ability. Copyright © 2024, The Authors. All rights reserved.

关键词： image coding

来源：评论

学校读者我要写书评

暂无评论

Scalable image coding for Human and Machines: Based on partial channel context model

Scalable Image Coding for Human and Machines: Based on parti...

引用

Chinese Control and Decision Conference, CCDC

作者： Yunhui Shi Jiawei Ren Lilong Wang Jin Wang Jiale Liu Faculty of Information Technology Beijing University of Technology Beijing China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

In recent years, there has been a substantial increase in the amount of visual data generated by edge devices. Machines typically process this data to accomplish tasks such as object detection without human visual judgment. However, human viewing is sometimes required during human-robot interaction. Here, there exists a significant difference in the focus of information between humans and machines. To tackle this issue, we propose an end-to-end learning-based image coding framework, aiming to strike a balance between human and machine vision tasks. Also, a portion of the latent space is used for both machine vision and human vision. This is different from a compression framework that only targets human vision. Because of this difference, correlations still exist between tasks. So we propose a partial-channel context model to improve coding *** scalable coding framework achieves simultaneous support for both human and machine vision by partitioning the latent space. Machine vision tasks are handled by a subset of the latent space, referred to as the base layer. More complex human visual reconstruction tasks are accomplished by an additional subset of the latent space, comprising both base and enhancement layers. In the experimental section, we present the performance of human visual reconstruction and machine vision tasks, comparing them with other benchmarks. The experiments demonstrate that our framework achieves a 28.27%-38.16% reduction in bitrate for machine vision tasks and matches the performance of state-of-the-art image codecs in terms of input reconstruction.

关键词： Visualization image coding Correlation Codecs Machine vision image edge detection Object detection

来源：评论

学校读者我要写书评

暂无评论

Adversarial Level of Face images Generated by Prompt-based image coding in Face Recognition System

Adversarial Level of Face Images Generated by Prompt-based I...

引用

IEEE Global Conference on Consumer Electronics (GCCE)

作者： Yurika Fujinami Hiroshi Watanabe School of FSE Waseda University Tokyo Japan

ISBN: (数字)9798350355079

ISBN: (纸本)9798350355086

In this study, we investigate the adversarial level of face images generated by a prompt-based image coding. The adversarial level is the criterion by which the image produced by diffusion is judged to be consistent with the unprocessed original image. The Prompt-based image coding is designed to combine semantic compression and faithful image representation. The quality of the coded image can be controlled by adjusting the amount of edge information. Face recognition systems rely on patches of faces formed by vectors created from feature points with significant edge contributions. It is therefore worth investigating how much facial edge information should be retained in prompt-based image coding to fool face recognition systems. Experimental results show high possibility of falsification when coded images are fed into the face recognition model.

关键词： Electric potential image coding Face recognition image edge detection Semantics Detectors image representation Vectors Consumer electronics

来源：评论

学校读者我要写书评

暂无评论

Unifying Generation and Compression: Ultra-low bitrate image coding Via Multi-stage Transformer

Unifying Generation and Compression: Ultra-low bitrate Image...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Naifu Xue Qi Mao Zijian Wang Yuan Zhang Siwei Ma School of Information and Communication Engineering Communication University of China Beijing China State Key Laboratory of Media Convergence and Communication Communication University of China Beijing China School of Electronics Engineering and Computer Science Peking University Beijing China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Recent progress in generative compression technology has significantly improved the perceptual quality of compressed data. However, these advancements primarily focus on producing high-frequency details, often overlooking the ability of generative models to capture the prior distribution of image content, thus impeding further bitrate reduction in extreme compression scenarios (< 0.05 bpp). Motivated by the capabilities of predictive language models for lossless compression, this paper introduces a novel Unified image Generation-Compression (UIGC) paradigm, merging the processes of generation and compression. A key feature of the UIGC framework is the adoption of vector-quantized (VQ) image models for tokenization, alongside a multi-stage transformer designed to exploit spatial contextual information for modeling the prior distribution. As such, the dual-purpose framework effectively utilizes the learned prior for entropy estimation and assists in the regeneration of lost tokens. Extensive experiments demonstrate the superiority of the proposed UIGC framework over existing codecs in perceptual quality and human perception, particularly in ultra-low bitrate scenarios (≤0.03 bpp), pioneering a new direction in generative compression.

关键词： Visualization image coding Codecs Bit rate Estimation Predictive models Transformers Entropy Tokenization Context modeling

来源：评论

学校读者我要写书评

暂无评论

Feature-Preserving Rate-Distortion Optimization in image coding for Machines

Feature-Preserving Rate-Distortion Optimization in Image Cod...

引用

IEEE Workshop on Multimedia Signal Processing

作者： Samuel Fernández-Menduiña Eduardo Pavez Antonio Ortega Department of Electrical and Computer Engineering University of Southern California Los Angeles California USA

ISBN: (数字)9798350387254

ISBN: (纸本)9798350387261

With the increasing number of images and videos consumed by computer vision algorithms, compression methods are evolving to consider both perceptual quality and performance in downstream tasks. Traditional codecs can tackle this problem by performing rate-distortion optimization (RDO) to minimize the distance at the output of a feature extractor. However, neural network non-linearities can make the rate-distortion landscape irregular, leading to reconstructions with poor visual quality even for high bit rates. Moreover, RDO decisions are made block-wise, while the feature extractor requires the whole image to exploit global information. In this paper, we address these limitations in three steps. First, we apply Taylor's expansion to the feature extractor, recasting the metric as an input-dependent squared error involving the Jacobian matrix of the neural network. Second, we make a localization assumption to compute the metric block-wise. Finally, we use randomized dimensionality reduction techniques to approximate the Jacobian. The resulting expression is monotonic with the rate and can be evaluated in the transform domain. Simulations with AVC show that our approach provides bit-rate savings while preserving accuracy in downstream tasks with less complexity than using the feature distance directly.

关键词： Jacobian matrices Measurement Dimensionality reduction Computer vision image coding Neural networks Rate-distortion Transforms Feature extraction Optimization

来源：评论

学校读者我要写书评

暂无评论

Redundancy Removal Module for Reducing the Bitrates of image coding for Machines

Redundancy Removal Module for Reducing the Bitrates of Image...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Zhongpeng Zhang Ying Liu Department of Computer Science and Engineering Santa Clara University Santa Clara CA USA

ISBN: (数字)9798350330991

ISBN: (纸本)9798350331004

With the popularity of the Internet of Things (IoT) and surveillance, the amount of image and video information collected by internet has exploded. On the one hand, transmitting the massive information requires plenty of bandwidth. On the other hand, processing these data requires tremendous manpower. In order to solve these two problems at the same time, image coding for machines (ICM) came into being. At present, most ICM technologies combine traditional codecs such as BPG or machine learning codecs such as the hyperprior codec and the coarse-to-fine codec with task networks such as image classification and semantic segmentation. This process requires the complete restoration of the image, which greatly increases the bitrates. Moreover, the restored images are for human eyes and contain a large amount of redundant information, which is not required by the task network. In order to solve this problem, side information driven image coding for machines (SIIC) was proposed, which only needs to input hyperprior information to the image classification network, which greatly reduces the scale of data transmission. Now, we propose a redundancy removal module that can further reduce the usage of bitrates for SIIC. Through this module, the new codec uses 3% to 4% less bitrates than the original SIIC when the bitrates are under 0.06 bpp, and can save up to 10% of bitrates when the bitrates are over 0.1 bpp.

关键词： Codecs image coding Surveillance Semantic segmentation Bit rate Redundancy image restoration

来源：评论

学校读者我要写书评

暂无评论

Neural Multiple Description image coding with Semantic Polarization for Lossy Channels

Neural Multiple Description Image Coding with Semantic Polar...

引用

IEEE Conference on Wireless Communications and Networking

作者： Yajing Liu Weicheng Zhang Lingyu Chen Xuemin Hong Xianbin Wang School of Informatics Xiamen University Xiamen China Department of Electrical and Computer Engineering Western University London Canada

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

Multiple description coding (MDC) is a type of error-resilient source coding that is advantageous for communications over channels with high loss and long delays. While neural network-based MDC promises higher compression efficiency and better semantic awareness, the aspect of semantic awareness is under-investigated. This paper is among the first efforts to study MDCs with competing performance goals known as the distortion-classification tradeoff. A new design concept called semantic polarization is proposed to contradict the traditional philosophy of balanced side encoder designs. We present a simple conceptual model to demonstrate the advantage of polarized MDC in having higher probabilities of satisfying at least one performance goal. We also propose a detailed implementation of polarized MDC based on SRGANs. Experiments on public datasets show that compared with state-of-the-art single description neural image codecs, the proposed MDC has multiple benefits in terms of enlarged rate range, superior semantic protection, and better perception quality, at the cost of slightly reduced but competitive distortion performance.

关键词： Measurement image coding Costs Codecs Philosophical considerations Source coding Semantics

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：