检索结果-内蒙古大学图书馆

Efficient Gradient-Domain Compositing Using an Approximate Curl-free Wavelet Projection

computer graphics FORUM 2017年第7期36卷 207-215页

作者： Ren, Xiaohua Lyu, Luan He, Xiaowei Zhang, Yanci Wu, Enhua Univ Macau Taipa Macao Peoples R China ISCAS State Key Lab CS Beijing Peoples R China Univ CAS Beijing Peoples R China Sichuan Univ Chengdu Sichuan Peoples R China Zhuhai UM Sci & Technol Res Inst Zhuhai Peoples R China

Gradient-domain compositing has been widely used to create a seamless composite with gradient close to a composite gradient field generated from one or more registered images. The key to this problem is to solve a Poisson equation, whose unknown variables can reach the size of the composite if no region of interest is drawn explicitly, thus making both the time and memory cost expensive in processing multi-megapixel images. In this paper, we propose an approximate projection method based on biorthogonal Multiresolution Analyses (MRA) to solve the Poisson equation. Unlike previous Poisson equation solvers which try to converge to the accurate solution with iterative algorithms, we use biorthogonal compactly supported curl-free wavelets as the fundamental bases to approximately project the composite gradient field onto a curl-free vector space. Then, the composite can be efficiently recovered by applying a fast inverse wavelet transform. Considering an n-pixel composite, our method only requires 2n of memory for all vector fields and is more efficient than state-of-the-art methods while achieving almost identical results. Specifically, experiments show that our method gains a 5x speedup over the streaming multigrid in certain cases.

关键词： Categories and Subject Descriptors (according to ACM CCS) I.3.3 [computer graphics]: Picture/Image Generation—Display algorithms

来源：评论

学校读者我要写书评

暂无评论

3D object compression using enhanced stripification technique

3D object compression using enhanced stripification techniqu...

引用

IEEE pacific Rim conference on Communications, computers and Signal Processing

作者： Fatma Khairy Mohamed H. Mousa Hamed Nassar Mohamed S. Yasein Department of Computer Science Suez Canal University Ismailia Egypt Department of Electrical and Computer Engineering Port Said University Port Said Egypt

3D meshes are one of the most common representations of 3D objects that have been used in graphics applications. They often require a huge amount of data for storage and/or transmission. In this paper, we present a new compression algorithm based on stripification of the geometric models that enables us to progressively visualize the 3D models during their transmission. The proposed algorithm encodes the geometry and the connectivity of the input model in an interwoven fashion. The main idea is to store 3D objects as strips files. The algorithm achieves compression ratios above 61 : 1 over ASCII encoded formats resulting in faster transmission and rendering of complex graphical objects.

关键词： Strips Joining processes Three dimensional displays Solid modeling Geometry Rendering (computer graphics) Compression algorithms

来源：评论

学校读者我要写书评

暂无评论

Automatic Parallelization of GPU applications Using OpenCL

Automatic Parallelization of GPU Applications Using OpenCL

引用

Asia-pacific conference on computer Aided System Engineering (APCASE)

作者： Lizandro D. Solano-Quinde Brett M. Bode Arun K. Somani Department of Electrical University of Cuenca Ecuador U.S. Department of Energy Ames Laboratory USA National Center for Supercomputing Applications University of Illinois at Urbana-Champaign USA Department of Electrical and Computer Engineering Iowa State University USA

graphics Processing Units (GPUs) have been successfully used to accelerate scientific applications due to their computation power and the availability of programming languages that make more approachable writing scientific applications for GPUs. However, since the programming model of GPUs requires offloading all the data to the GPU memory, the memory footprint of the application is limited to the size of the GPU memory. Multi-GPU systems can make memory limited problems tractable by parallelizing the computation and data among the available GPUs. Parallelizing applications written for running on single-GPU systems can be done (i) at runtime through an environment that captures the memory operations and kernel calls and distributes among the available GPUs, and (ii) at compile time through a pre-compiler that transforms the application for decomposing the data and computation among the available GPUs. In this paper we propose a framework and implement a tool that transforms an OpenCL application written to run on single-GPU systems into one that runs on multi-GPU systems. Based on data dependencies and data usage analysis, the application is transformed to decompose data and computation among the available GPUs. To reduce the data transfer overhead, computation-communication overlapping techniques are utilized. We tested our tool using two applications with different data transfer requirements, for the application with no data transfer requirements, a linear speedup is achieved, while for the application with data transfers, the computation-communication overlapping reduces the communication overhead by 40%.

关键词： Kernel Arrays graphics processing units Data transfer Algorithms XML Memory management

来源：评论

学校读者我要写书评

暂无评论

An architectural extension to the media core processor for HDTV applications

An architectural extension to the media core processor for H...

引用

IEEE Asia-pacific conference on Circuits and Systems

作者： K. Yoshioka H. Oka H. Nishida R. Matsuura T. Kiyohara Matsushita Elecrric Indusrrial Company Limited Kadoma Osaka Japan

Introduces an architectural extension to the media core processor (MCP), which targets a system solution for consumer multimedia products. This extension implements HDTV video decoding (1080i, 720p, 480p and 480i), video resizing, 2-D graphics rendering, and conversion between various video formats for data broadcasting. For pixel-level operations in HDTV applications, a SIMD-style processor has been introduced. However, image resizing causes a difference in data structure between source and result dynamically. Therefore, an advanced inter-PE (processing element) communication mechanism is necessary as an extension to the common SIMD-style architecture. This processor achieves the flexibility of pixel-level operation and the efficiency of high bandwidth. Adopting this new MCP architecture enabled us to improve image quality to fulfill the requirements for consumer products.

关键词： HDTV Videos Decoding graphics Rendering (computer graphics) Image converters Multimedia communication Data structures Bandwidth Image quality

来源：评论

学校读者我要写书评

暂无评论

BSTC: A Novel Binarized-Soft-Tensor-Core Design for Accelerating Bit-Based Approximated Neural Nets 19

BSTC: A Novel Binarized-Soft-Tensor-Core Design for Accelera...

引用

International conference for High Performance Computing, Networking, Storage and Analysis (SC)

作者： Li, Ang Geng, Tong Wang, Tianqi Herbordt, Martin Song, Shuaiwen Leon Barker, Kevin Pacific Northwest Natl Lab Richland WA 99352 USA Boston Univ Boston MA 02215 USA

ISBN: (数字)9781450362290

ISBN: (纸本)9781450362290

Binarized neural networks (or BNNs) promise tremendous performance improvement over traditional DNNs through simplified bit-level computation and significantly reduced memory access/storage cost. In addition, it has advantages of low-cost, low-energy, and high-robustness, showing great potential in resources-constrained, volatile, and latency-critical applications, which are critical for future HPC, cloud, and edge applications. However, the promised significant performance gain of BNN inference has never been fully demonstrated on general-purpose processors, particularly on GPUs, due to: (i) the challenge of extracting and leveraging sufficient fine-grained bit-level-parallelism to saturate GPU cores when the batch size is small;(ii) the fundamental design conflict between bit-based BNN algorithm and word-based architecture;and (iii) architecture & performance unfriendly to BNN network design. To address (i) and (ii), we propose a binarized-soft-tensor-core as a software-hardware c o design approach to construct bit-manipulation capability for modern GPUs and thereby effectively harvest bit-level-parallelism (BLP). To tackle (iii), we propose intra- and inter-layer fusion techniques so that the entire BNN inference execution can be packed into a single GPU kernel, and so avoid the high-cost of frequent launching and releasing. Experiments show that our Singular-Binarized-NeuralNetwork (SBNN) design can achieve over 1000x speedup for raw inference latency over the state-of-the-art full-precision BNN inference for AlexNet on GPUs. Comparisons with CPU, GPU, FPGA and Xeon-Phi demonstrate the effectiveness of our design. SBNN is opensourced and available at https://***/uuudown/SBNIV.

关键词： Costs High performance computing Neural networks graphics processing units computer architecture Performance gain Inference algorithms Kernel Field programmable gate arrays

来源：评论

学校读者我要写书评

暂无评论

Multiresolution Point Cloud Compression for Real-Time Visualization and Streaming of Large 3D Datasets 58

Multiresolution Point Cloud Compression for Real-Time Visual...

引用

58th Asilomar conference on Signals, Systems and computers, ACSSC 2024

作者： Nguyen, Dat Thanh Zieger, Daniel Gambietz, Markus Koelewijn, Anne D. Stamminger, Marc Kaup, André Multimedia Communications and Signal Processing Erlangen Germany Visual Computing Erlangen Germany Erlangen Germany

ISBN: (纸本)9798350354058

In recent years, the integration of point cloud data has been observed across diverse domains such as immersive media, autonomous driving, and healthcare. However, processing and visualizing 3D point cloud data requires more computational power and processing time than typical 2D images or videos. In this paper, we present a multiresolution point cloud visualization approach that enables the encoding and reconstruction of human body point clouds at multiple quality/bitrate levels for streaming or real-time visualization applications. Specifically, we partition the 3D model into cells and build an octree structure to store the point cloud at multiple levels of detail. The hierarchical structure is encoded efficiently for fast loading times. We optimize the resolution selection for each visible node based on the camera viewpoint and the geometric error perceived by the user. We validate the proposed method using a widely known point cloud dataset from the Moving Picture Experts Group. The experiments demonstrate that the method can dynamically adapt the resolution of point clouds and provide faster rendering times compared to well-known point cloud visualization software. © 2024 IEEE.

关键词： Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Design of a scalable many-core processor for embedded applications

Design of a scalable many-core processor for embedded applic...

引用

Asia and South pacific Design Automation conference

作者： Hsiao-Wei Chien Jyun-Long Lai Chao-Chieh Wu Chih-Tsun Huang Ting-Shuo Hsu Jing-Jia Liou Department of Computer Science National Tsing Hua University Hsinchu Taiwan Department of Electrical Engineering National Tsing Hua University Hsinchu Taiwan

ISBN: (纸本)9781479977932

We present a novel design of scalable many-core processor with its comprehensive development framework, including the Electronic System Level, Register Transfer Level, and full-system prototyping platforms. Architecture exploration, performance evaluation and system verification/validation can be done across different abstraction levels. With our hardware-independent software layer, applications built on top of the fast virtual platform can be executed seamlessly on the prototype. The emulation result justifies the effectiveness of our processor architecture in embedded applications.

关键词： computer architecture Software System-on-chip Hardware Three-dimensional displays graphics Emulation

来源：评论

学校读者我要写书评

暂无评论

Accelerated biomedical simulations using the FDTD method and the CUDA architecture

Accelerated biomedical simulations using the FDTD method and...

引用

Asia-pacific conference on Microwave

作者： David Ireland Wei Chern Tee Marek Bialkowski School of ITEE University of Queensland Brisbane Australia

This paper presents empirical results of the finite difference time domain algorithm implemented on NVIDIA's CUDA architecture in order to achieve significant decreases in electromagnetic field simulation time. The proposed strategy is demonstrated with respect to biomedical applications where 10 different anatomical realistic body phantoms are simulated and speed increases quantified.

关键词： Phantoms graphics processing unit Finite difference methods Time domain analysis Breast computer architecture Throughput

来源：评论

学校读者我要写书评

暂无评论

The PDI crowd system for ANTZ 98

The PDI crowd system for ANTZ

引用

ACM SIGGRAPH 98 conference abstracts and applications

作者： Luca Prasso Juan Buhler Jonathan Gibbs Pacific Data Images Palo Alto CA

No abstract available.

ISBN: (纸本)9781581130461

No abstract available.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TEASAR: tree-structure extraction algorithm for accurate and robust skeletons

TEASAR: tree-structure extraction algorithm for accurate and...

引用

pacific conference on computer graphics and applications

作者： M. Sato I. Bitter M.A. Bender A.E. Kaufman M. Nakajima Department of Computer Science Tokyo Institute of Technology Japan Department of Computer Science State University of New York Stony Brook USA

ISBN: (纸本)0769508685

We introduce the TEASAR algorithm which is a treestructure extraction algorithm delivering skeletons that are accurate and robust. Volumetric skeletons are needed for accurate measurements of length along branching and winding structures. Skeletons are also required in automatic virtual navigation, such as traveling through human organs (e.g., the colon) to control movement and orientation of the virtual camera. We introduce a concise but general definition of a skeleton, and provide an algorithm that finds the skeleton accurately and rapidly. Our solution is fully automatic, which frees the user from having to engage in data preprocessing. We present the accurate skeletons computed on a number of test datasets. The algorithm is efficient as demonstrated by the running times on a single 194 MHz MIPS R10000 CPU which were all below five minutes.

关键词： Robustness Skeleton Length measurement Volume measurement Navigation Humans Colon Automatic control Cameras Data preprocessing

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：