检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Glaszner, Lukas Zach, Martin Institute of Computer Graphics and Vision Graz University of Technology Inffeldgasse 16/II Graz8010 Austria Biomedical Imaging Group École polytechnique fédérale de Lausanne Lausanne1015 Switzerland Center for Biomedical Imaging Lausanne1015 Switzerland

Diffusion model have been successfully applied to many inverse problems, including MRI and CT reconstruction. Researchers typically re-purpose models originally designed for unconditional sampling without modifications. Using two different posterior sampling algorithms, we show empirically that such large networks are not necessary. Our smallest model, effectively a ResNet, performs almost as good as an attention U-Net on in-distribution reconstruction, while being significantly more robust towards distribution shifts. Furthermore, we introduce models trained on natural images and demonstrate that they can be used in both MRI and CT reconstruction, out-performing model trained on medical images in out-of-distribution cases. As a result of our findings, we strongly caution against simply re-using very large networks and encourage researchers to adapt the model complexity to the respective task. Moreover, we argue that a key step towards a general diffusion-based prior is training on natural images. © 2025, CC BY-SA.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

One-sided Frank-Wolfe algorithms for saddle problems

arXiv

引用

arXiv 2021年

作者： Kolmogorov, Vladimir Pock, Thomas Institute of Science and Technology Austria Institute of Computer Graphics and Vision Graz University of Technology

We study a class of convex-concave saddle-point problems of the form minx maxy(Kx, y) + fP(x) - h∗(y) where K is a linear operator, fP is the sum of a convex function f with a Lipschitz-continuous gradient and the indicator function of a bounded convex polytope P, and h∗ is a convex (possibly nonsmooth) function. Such problem arises, for example, as a Lagrangian relaxation of various discrete optimization problems. Our main assumptions are the existence of an efficient linear minimization oracle (lmo) for fP and an efficient proximal map (prox) for h∗ which motivate the solution via a blend of proximal primal-dual algorithms and Frank-Wolfe algorithms. In case h∗ is the indicator function of a linear constraint and function f is quadratic, we show a O(1/n2) convergence rate on the dual objective, requiring O(n log n) calls of lmo. If the problem comes from the constrained optimization problem minx∈d{fP(x) | Ax - b = 0} then we additionally get bound O(1/n2) both on the primal gap and on the infeasibility gap. In the most general case, we show a O(1/n) convergence rate of the primal-dual gap again requiring O(n log n) calls of lmo. To the best of our knowledge, this improves on the known convergence rates for the considered class of saddle-point problems. We show applications to labeling problems frequently appearing in machine learning and computer vision. Copyright © 2021, The Authors. All rights reserved.

关键词： Mathematical operators

来源：评论

学校读者我要写书评

暂无评论

In-Hand 3D Object Scanning from an RGB Sequence

In-Hand 3D Object Scanning from an RGB Sequence

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Shreyas Hampali Tomas Hodan Luan Tran Lingni Ma Cem Keskin Vincent Lepetit Reality Labs at Meta LIGM Ecole des Ponts Univ Gustave Eiffel CNRS Marne-la-Vallée France Institute for Computer Graphics and Vision Graz University of Technology Graz Austria

We propose a method for in-hand 3D scanning of an unknown object with a monocular camera. Our method relies on a neural implicit surface representation that captures both the geometry and the appearance of the object, however, by contrast with most NeRF-based methods, we do not assume that the camera-object relative poses are known. Instead, we simultaneously optimize both the object shape and the pose trajectory. As direct optimization over all shape and pose parameters is prone to fail without coarse-level initialization, we propose an incremental approach that starts by splitting the sequence into carefully selected overlapping segments within which the optimization is likely to succeed. We reconstruct the object shape and track its poses independently within each segment, then merge all the segments before performing a global optimization. We show that our method is able to reconstruct the shape and color of both textured and challenging texture-less objects, outperforms classical methods that rely only on appearance features, and that its performance is close to recent methods that assume known camera poses.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On Evaluating Pixel-Level Face Image Quality Assessment

On Evaluating Pixel-Level Face Image Quality Assessment

引用

European Signal Processing Conference (EUSIPCO)

作者： Marco Huber Philipp Terhöst Florian Kirchbuchner Naser Damer Arjan Kuijper Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Department of Computer Science TU Darmstadt Darmstadt Germany Norwegian University of Science and Technology Gjϕvik Norway

ISBN: (数字)9789082797091

ISBN: (纸本)9781665467995

A decisive factor for face recognition performance is face image quality (FIQ). It describes the utility of face images for automatic recognition. While this FIQ has conventionally been considered as a scalar for the whole image, emerging works suggest assessing pixel-level FIQs to provide higher explainability. However, the value of pixel-level qualities as a measure of utility (value for recognition) is not yet investigated. In this work, we address this by presenting two evaluation schemes, deletion evaluation curve (DEC) and insertion evaluation curve (IEC). The DEC investigates the change in recognition performance as pixels are deleted based on their quality. Complementary, the IEC reports the change in recognition performance as pixels are inserted based on their quality into a blurred image. Since pixel-level face image quality assessment (PLFIQA) methods assign high values to pixels that contain discriminant information, the recognition performance should decrease or increase when they are removed or added, respectively. We have successfully demonstrated the proposed evaluation scheme on two face recognition solutions by comparing a recently proposed PLFIQA method to a random baseline. With the growing interest in explainable face recognition, the proposed metrics will enable adequate comparison of future advances in pixel-level quality assessment.

关键词： Image quality Measurement Image recognition Face recognition Biological system modeling IEC Europe

来源：评论

学校读者我要写书评

暂无评论

Research of Virtual Simulation Experiment Course Resource Intelligent Information System Construction 2

Research of Virtual Simulation Experiment Course Resource In...

引用

2nd IEEE International Conference on Power, Electronics and computer Applications, ICPECA 2022

作者： Wang, Yangping Dang, Jianwu Yong, Jiu Wang, Wenrun Yue, Biao Jin, Fangrui Computer Science and Technology Experimental Teaching Demonstration Center of National Lanzhou Jiaotong University National Virtual Simulation Experiment Teaching Center of Railway Traffic Information and Control Lanzhou Jiaotong University Gansu Prov. Eng. Research Center for Artificial Intelligence and Graphics and Image Processing Lanzhou730070 China National Virtual Simulation Experiment Teaching Center of Railway Traffic Information and Control Lanzhou Jiaotong University College of Intelligence and Computing Tianjin University Computer Science and Technology Experimental Teaching Demonstration Center of National Lanzhou Jiaotong University Gansu Prov. Eng. Research Center for Artificial Intelligence and Graphics and Image Processing Lanzhou730070 China College of Electronic and Information Engineering Lanzhou Jiaotong University Gansu Provincial Engineering Research Center for Artificial Intelligence and Graphics and Image Processing Lanzhou730070 China

ISBN: (纸本)9781665442763

In order to enable the construction of virtual simulation experiment resources in colleges and universities to keep up with the development of professional technology, this paper proposes to build a 'diversified virtual simulation experiment teaching resource construction system' through exploration and research. With the help of virtual reality, AR, panoramic roaming, video and other technologies, it provides a unified development framework, development documents and case templates for professional teachers to independently develop virtual simulation experiment teaching resources in line with undergraduate teaching, and helps teachers quickly build virtual simulation experiment resources in accordance with unified standards. It effectively solves the problems that it is difficult for college teachers to independently develop virtual simulation courseware and the technology is not unified. © 2022 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Fast reconstruction of multiphase microstructures based on statistical descriptors

引用

Physical Review E 2022年第5期105卷 055301-055301页

作者： DongDong Chen Zhi Xu XiaoRui Wang HongJie He ZhongZhou Du JiaoFen Nan School of Computer and Communication Engineering Zhengzhou University of Light Industry Zhengzhou 450000 China Guangxi Key Laboratory of Images and Graphics Intelligent Processing Guilin University of Electronics Technology Guilin 541004 China

In this paper, we propose a hierarchical simulated annealing of erosion method (HSAE) to improve the computational efficiency of multiphase microstructure reconstruction, whose computational efficiency can be improved by an order of magnitude. Reconstruction of the two-dimensional (2D) and three-dimensional (3D) multiphase microstructures (pore, grain, and clay) based on simulated annealing (SA) and HSAE are performed. In the reconstruction of multiphase microstructure with HSAE and SA, three independent two-point correlation functions are chosen as the morphological information descriptors. The two-point cluster function which contains significant high-order statistical information is used to verify the reconstruction results. From the analysis of 2D reconstruction, it can find that the proposed HSAE technique not only improves the quality of reconstruction, but also improves the computational efficiency. The reconstructions of our proposed method are still imperfect. This is because the used two-point correlation functions contain insufficient information. For the 3D reconstruction, the two-point correlation functions of the 3D generation are in excellent agreement with those of the original 2D image, which illustrates that our proposed method is effective for the reconstruction of 3D microstructure. The comparison of the energy vs computational time between the SA and HSAE methods shows that our presented method is an order of magnitude faster than the SA method. That is because only some of the pixels in the overall hierarchy need to be considered for sampling.

关键词： Stochastic processes Stochastic processes & statistics

来源：评论

学校读者我要写书评

暂无评论

Web-Based Service Development for Intellectual Maintenance of the Personalized Educational and Professional Program : Adaptive provision of educational services in academic mobility context through automated improvement of quality and relevance of tutorial content

Web-Based Service Development for Intellectual Maintenance o...

引用

International computer Sciences and Information Technologies (CSIT)

作者： Tetyana Neroda Lidiia Slipchyshyn Department of Automation and Computer technology Ukrainian Academy of Printing Lviv Ukraine Department of Theory and Methods of Technological Education Drawing and Computer Graphics National Pedagogical Drahomanov University Kyiv Ukraine

ISBN: (纸本)9798350334326

The results of empirical analysis of conceptual sources in the direction of educational methods comparison for optimizing the teaching loads for engineering education applicants are presented. Disadvantages and potential conflicts of trainee when mastering of educational and professional program content are formalized, in particular within academic mobility frameworks, as well as in view of the rapid increase in the number of academic refugees. Among the recommended ways of solving problems with academic arrears accumulation, is the information and communication technology of matching the optimally combined educational content to soft compensate for the knowledge and skills that student’s lacks. The relevance of automated quality improvement and propriety of tutorial content is substantiated, and sets of software functionalities of web-based service for teaching loads personalization are determined, which were localized by departments of academic information space for purpose of integration into a united cross-academic communication system. Proposals regarding the reorganization of the structure of digitized methodical and information supports of the educational process according to the mosaic principle have been formulated. On basis of the developed analytical apparatus, a communication model of the network infrastructure of teaching loads optimization service was built, which provides a targeted selection of tutorial media content from problematic domain of subject in file storages of university library collections and confidential faculty funds and distributes according to the forms of educational process on the end terminal of the authorized user.

关键词： Analytical models Tutorials Media Maintenance engineering Software Libraries Proposals

来源：评论

学校读者我要写书评

暂无评论

Video Test-Time Adaptation for Action Recognition

Video Test-Time Adaptation for Action Recognition

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Wei Lin Muhammad Jehanzeb Mirza Mateusz Kozinski Horst Possegger Hilde Kuehne Horst Bischof Institute for Computer Graphics and Vision Graz University of Technology Austria Christian Doppler Laboratory for Semantic 3D Computer Vision Christian Doppler Laboratory for Embedded Machine Learning Goethe University Frankfurt Germany MIT-IBM Watson AI Lab

Although action recognition systems can achieve top performance when evaluated on in-distribution test points, they are vulnerable to unanticipated distribution shifts in test data. However, test-time adaptation of video action recognition models against common distribution shifts has so far not been demonstrated. We propose to address this problem with an approach tailored to spatio-temporal models that is capable of adaptation on a single video sample at a step. It consists in a feature distribution alignment technique that aligns online estimates of test set statistics towards the training statistics. We further enforce prediction consistency over temporally augmented views of the same test video sample. Evaluations on three benchmark action recognition datasets show that our proposed technique is architecture-agnostic and able to significantly boost the performance on both, the state of the art convolutional architecture TANet and the Video Swin Transformer. Our proposed method demonstrates a substantial performance gain over existing test-time adaptation approaches in both evaluations of a single distribution shift and the challenging case of random distribution shifts. Code will be available at https://***/wlin-at/ViTTA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MCTS with Refinement for Proposals Selection Games in Scene Understanding

arXiv

引用

arXiv 2022年

作者： Stekovic, Sinisa Rad, Mahdi Moradi, Alireza Fraundorfer, Friedrich Lepetit, Vincent Institute for Computer Graphics and Vision Graz University of Technology Graz Austria Université Paris-Est École des Ponts ParisTech Paris France

We propose a novel method applicable in many scene understanding problems that adapts the Monte Carlo Tree Search (MCTS) algorithm, originally designed to learn to play games of high-state complexity. From a generated pool of proposals, our method jointly selects and optimizes proposals that minimize the objective term. In our first application for floor plan reconstruction from point clouds, our method selects and refines the room proposals, modelled as 2D polygons, by optimizing on an objective function combining the fitness as predicted by a deep network and regularizing terms on the room shapes. We also introduce a novel differentiable method for rendering the polygonal shapes of these proposals. Our evaluations on the recent and challenging Structured3D and Floor-SP datasets show significant improvements over the state-of-the-art, without imposing hard constraints nor assumptions on the floor plan configurations. In our second application, we extend our approach to reconstruct general 3D room layouts from a color image and obtain accurate room layouts. We also show that our differentiable renderer can easily be extended for rendering 3D planar polygons and polygon embeddings. Our method shows high performance on the Matterport3D-Layout dataset, without introducing hard constraints on room layout configurations. Copyright © 2022, The Authors. All rights reserved.

关键词： Floors

来源：评论

学校读者我要写书评

暂无评论

The Study of the Classic Producer-consumer Problem in a Series of IT Courses 20

The Study of the Classic Producer-consumer Problem in a Seri...

引用

21st Annual Conference of the Special Interest Group in Information technology Education, SIGITE 2020

作者： Luo, Ying Wang, Xianping Purdue University Northwest Dept. of Computer Information Technology and Graphics HammondIN United States

ISBN: (纸本)9781450370455

It is a time-consuming task for the instructors to design the examples, assignments, and projects to meet the requirement of learning outcomes. Luckily, most of the courses in information technology major are relevant and some are closely related to each other. Therefore, we propose to take advantage of the same problem which can be analyzed from different aspects under a series of IT courses. It will not only reduce the burden of the instructors to design the brand-new exercises but also help students quickly understand the foundation of the problem from what they studied and embark on exploring the high-level topics in new courses. In this paper, we use the classic producer-consumer problem as an example to present our proposition. This problem is generally shown up in operating systems course to illustrate the multi-process synchronization. We expand this problem from different angels and motivate the students to further explore other relevant topics: The objects? datatypes, properties, functions are declared in programming course and the built-in thread feature in some specific language like Java can also be demonstrated by this problem's solution. The design of data structure of the producer, the consumer, and the buffer can be discussed in data structure course. The collaboration between the producer and the consumer can be used for explaining the cause of deadlock in database course. Finally, the producer-consumer problem is used to clarify different application architectures in application/software design course. We expect that our methodology on IT education can illumine other educators looking to the similar mode in their program. © 2020 ACM.

关键词： Data structures

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：