检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Guo, Qianyu Yu, Ziqing Fu, Jiaming Lu, Yawen Zweiri, Yahya Gan, Dongming The School of Engineering Technology Purdue University United States The Computer Graphics Technology Department Purdue University United States Khalifa University United Arab Emirates

Robotic grippers are receiving increasing attention in various industries as essential components of robots for interacting and manipulating objects. While significant progress has been made in the past, conventional rigid grippers still have limitations in handling irregular objects and can damage fragile objects. We have shown that soft grippers offer deformability to adapt to a variety of object shapes and maximize object protection. At the same time, dynamic vision sensors (e.g., event-based cameras) are capable of capturing small changes in brightness and streaming them asynchronously as events, unlike RGB cameras, which do not perform well in low-light and fast-moving environments. In this paper, a dynamic-vision-based algorithm is proposed to measure the force applied to the gripper. In particular, we first set up a DVXplorer Lite series event camera to capture twenty-five sets of event data. Second, motivated by the impressive performance of the Vision Transformer (ViT) algorithm in dense image prediction tasks, we propose a new approach that demonstrates the potential for real-time force estimation and meets the requirements of real-world scenarios. We extensively evaluate the proposed algorithm on a wide range of scenarios and settings, and show that it consistently outperforms recent approaches. © 2024, CC BY-NC-SA.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

CUDA and Applications to Task-based Programming

CUDA and Applications to Task-based Programming

引用

42nd Annual Conference on European Association for computer graphics, EUROgraphics 2021

作者： Kenzel, M. Kerbl, B. Winter, M. Steinberger, M. Saarland University Computer Graphics Lab Germany TU Wien Institute of Visual Computing and Human-Centered Technology Austria Graz University of Technology Institute of Computer Graphics and Vision Austria

ISBN: (纸本)9783038681359

Since its inception, the CUDA programming model has been continuously evolving. Because the CUDA toolkit aims to consistently expose cutting-edge capabilities for general-purpose compute jobs to its users, the added features in each new version reflect the rapid changes that we observe in GPU architectures. Over the years, the changes in hardware, growing scope of built-in functions and libraries, as well as an advancing C++ standard compliance have expanded the design choices when coding for CUDA, and significantly altered the directives to achieve peak performance. In this tutorial, we give a thorough introduction to the CUDA toolkit, demonstrate how a contemporary application can benefit from recently introduced features and how they can be applied to task-based GPU scheduling in particular. For instance, we will provide detailed examples of use cases for independent thread scheduling, cooperative groups, and the CUDA standard library, libcu++, which are certain to become an integral part of clean coding for CUDA in the near future. © 2021 The Author(s).

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

Free-Viewpoint Visual Inspection via 3D Gaussian Splatting for Direct Template Matching

Free-Viewpoint Visual Inspection via 3D Gaussian Splatting f...

引用

Annual Conference of Industrial Electronics Society

作者： Kenta Ito Shiori Ueda Shohei Mori Junichi Sugano Hideyuki Adachi Hideo Saito Information and Computer Science Keio University Yokohama Japan Institute of Computer Graphics and Vision Graz University of Technology Graz Austria ViSCO Technologies Corporation Tokyo Japan

ISBN: (数字)9781665464543

ISBN: (纸本)9781665464550

Machine vision systems play a pivotal role in streamlining manufacturing processes, notably in quality control through automatic in-line visual inspections. A common practice for inspecting parts, components, and final products is to use a master part benchmark for quality comparison. However, challenges arise when objects enter inspection points in unintended orientations. This misalignment potentially leads to erroneous decisions by automated systems, resulting in additional checkpoints or wastage affecting the production rate. To tackle this issue, we propose a visual inspection pipeline that leverages recent machine learning-based approaches to compare the inspection target and a master part virtually oriented to the same perspective. Specifically, we suggest combining 3D Gaussian Splatting and DUSt3R as a practical solution. Our approach demonstrates its efficacy in real-world scenarios through testing on three mock parts and a real industrial component.

关键词： Visualization Three-dimensional displays Manufacturing processes Machine vision Pipelines Pose estimation Prototypes Production Quality control Inspection

来源：评论

学校读者我要写书评

暂无评论

SelfMAD: Enhancing Generalization and Robustness in Morphing Attack Detection via Self-Supervised Learning

arXiv

引用

arXiv 2025年

作者： Ivanovska, Marija Todorov, Leon Damer, Naser Jain, Deepak Kumar Peer, Peter Štruc, Vitomir Faculty of Electrical Engineering University in Ljubljana Slovenia Faculty of Computer and Information Science University in Ljubljana Slovenia Dalian University of Technology China Fraunhofer Institute for Computer Graphics Research Germany

With the continuous advancement of generative models, face morphing attacks have become a significant challenge for existing face verification systems due to their potential use in identity fraud and other malicious activities. Contemporary Morphing Attack Detection (MAD) approaches frequently rely on supervised, discriminative models trained on examples of bona fide and morphed images. These models typically perform well with morphs generated with techniques seen during training, but often lead to sub-optimal performance when subjected to novel unseen morphing techniques. While unsupervised models have been shown to perform better in terms of generalizability, they typically result in higher error rates, as they struggle to effectively capture features of subtle artifacts. To address these shortcomings, we present SelfMAD, a novel self-supervised approach that simulates general morphing attack artifacts, allowing classifiers to learn generic and robust decision boundaries without overfitting to the specific artifacts induced by particular face morphing methods. Through extensive experiments on widely used datasets, we demonstrate that SelfMAD significantly outperforms current state-of-the-art MADs, reducing the detection error by more than 64% in terms of EER when compared to the strongest unsupervised competitor, and by more than 66%, when compared to the best performing discriminative MAD model, tested in cross-morph settings. The source code for SelfMAD is available at https://***/LeonTodorov/SelfMAD. © 2025, CC BY-NC-ND.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Joint Non-Linear MRI Inversion with Diffusion Priors

arXiv

引用

arXiv 2023年

作者： Erlacher, Moritz Zach, Martin Graz Univeristy of Technology Institute of Computer Graphics and Vision Inffeldgasse 16/II Graz8010 Austria

Magnetic resonance imaging (MRI) is a potent diagnostic tool, but suffers from long examination times. To accelerate the process, modern MRI machines typically utilize multiple coils that acquire sub-sampled data in parallel. Data-driven reconstruction approaches, in particular diffusion models, recently achieved remarkable success in reconstructing these data, but typically rely on estimating the coil sensitivities in an off-line step. This suffers from potential movement and misalignment artifacts and limits the application to Cartesian sampling trajectories. To obviate the need for off-line sensitivity estimation, we propose to jointly estimate the sensitivity maps with the image. In particular, we utilize a diffusion model — trained on magnitude images only — to generate high-fidelity images while imposing spatial smoothness of the sensitivity maps in the reverse diffusion. The proposed approach demonstrates consistent qualitative and quantitative performance across different sub-sampling patterns. In addition, experiments indicate a good fit of the estimated coil sensitivities. © 2023, CC BY.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Efficient Image Super-Resolution via Symmetric Visual Attention Network

Efficient Image Super-Resolution via Symmetric Visual Attent...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Qinrui Fan Chengxu Wu Shu Hu Xi Wu Xin Wang Jing Hu School of Computer Chengdu University of Information Technology Chengdu China Department of Computer Information and Graphics Technology Indiana University–Purdue University Indianapolis IN USA School of Public Health University at Albany SUNY USA

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

In recent years, efficient super-resolution research has focused on reducing model complexity and improving efficiency by leveraging deep small-kernel convolution, but it has the problem of a small receptive field, which leads to a limited ability of the network to reconstruct details. Large kernel convolution can provide a large receptive field and lead to a substantial enhancement in the quality of image reconstruction, but its computational cost is too high. To minimize the model’s parameter count and achieve efficient super-resolution reconstruction, this study introduces a symmetric visual attention network. The network decomposes the large kernel convolution into three different lightweight and efficient convolutions. It then forms a bottleneck structure by leveraging the varied receptive field sizes of these convolutions in combination. The attention mechanism is integrated to create a bottleneck attention module, enhancing the network’s feature awareness. Furthermore, the bottleneck attention modules are symmetrically arranged to construct a symmetric large kernel attention block, thereby further enhancing the network’s capability to extract deep features. The experimental results demonstrate that the proposed model achieves competitive quantitative metrics when compared to other lightweight super-resolution methods, and the details of the reconstructed images are enhanced. With only 183K parameters, the model achieves a lightweight yet high-quality super-resolution model, offering a novel solution approach for efficient super-resolution.

关键词： Training Measurement Visualization Convolution Computational modeling Superresolution Neural networks

来源：评论

学校读者我要写书评

暂无评论

P2LNet: HD Map Validation Using Graph Neural Networks

P2LNet: HD Map Validation Using Graph Neural Networks

引用

Robotics, Engineering, Science, and technology (RESTCON), International Conference on

作者： Jeevan Reji Vaibhav Omanwar Department of Computer Science Birla Institute of Technology & Sciences Pilani Hyderabad Campus India Nvidia Graphics Pvt Ltd Pune India

HD Maps are a highly important part of the autonomous driving stack to perform the activities of localization and route planning on the road. Therefore, HD Map Validation is crucial to ensure the HD Maps represent the road information as accurately as possible. While heuristics have been developed to validate HD Maps with reasonable accuracy, they are unable to solve the challenging path to traffic light validation problem of HD Map junctions. Based on the success of Graph Neural Network approaches on HD Map problems, such as Vector net, we propose the P2LNet. This P2LNet architecture consists of a fully connected subgraph followed by a Graph Encoder-Decoder Architecture that finally predicts the correct associations that would exist between paths and traffic lights in the junction. We trained and evaluated P2LNet on our in-house HD Map junction dataset, with P2LNet showing 94% accuracy on predicting the correct labels for the associations from a test set. While the results could be further improved by using edge features, P2LNet provides a significant accuracy in validating incorrect light associations. It also shows how GNN based approaches can be used to solve other significant HD Map and validation issues.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Hierarchical Variational Autoencoders for World Models in Reinforcement Learning

Deep Hierarchical Variational Autoencoders for World Models ...

引用

First International Conference on Transdisciplinary AI (TransAI)

作者： Sriharshitha Ayyalasomayajula Banafsheh Rekabdar Christos Mousas Department of Computer Science Portland State University Portland OR USA Department of Computer Graphics Technology Purdue University West Lafayette IN USA

With the increasing demand for sample-efficient and robust reinforcement learning agents, particularly in intricate domains like robotics, healthcare, and gaming, there is a strong need to minimize the computational overhead caused by the interactions between real and virtual agents. This necessitates highly accurate models to simulate virtual agents and limit the number of such interactions. To this effect, model-based reinforcement learning (MBRL) has been proven very effective in formulating an environment with superior decision-making and higher learning efficiency. A known approach in MBRL is World Models, which uses a generative engine called Variational Autoencoders (VAE). VAE utilizes a relatively simple architecture constrained in processing power for complex image inputs. Therefore, the image reconstruction error is high. Recent research in VAEs has shown poor reconstruction quality. This paper proposes a Nouveau VAE (NVAE) based World Models to address the abovementioned limitations. NVAE, which employs deep convolutions in its architecture, is employed as the visual sensory component of the World Models and is used to encode the environment dynamics into a latent representation. We show that NVAE-based World Models perform exceptionally well in the dream environment of car racing-v2 (OpenAI GYM env), improving the agent's performance by 45%. We then demonstrate that the NVAE-based World Models can be applied to robotic simulation environments like panda-gym, where the agent achieved a 95 % success rate in solving the reach task.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TEST-TIME ADVERSARIAL DETECTION AND ROBUSTNESS FOR LOCALIZING HUMANS USING ULTRA WIDE BAND CHANNEL IMPULSE RESPONSES

arXiv

引用

arXiv 2022年

作者： Kolli, Abhiram Mirza, Muhammad Jehanzeb Possegger, Horst Bischof, Horst Institute of Computer Graphics and Vision Graz University of Technology Austria

Keyless entry systems in cars are adopting neural networks for localizing its operators. Using test-time adversarial defences equip such systems with the ability to defend against adversarial attacks without prior training on adversarial samples. We propose a test-time adversarial example detector which detects the input adversarial example through quantifying the localized intermediate responses of a pre-trained neural network and confidence scores of an auxiliary softmax layer. Furthermore, in order to make the network robust, we extenuate the non relevant features by non-iterative input sample clipping. Using our approach, mean performance over 15 levels of adversarial perturbations is increased by 55.33% for the fast gradient sign method (FGSM) and 6.3% for both the basic iterative method (BIM) and the projected gradient method (PGD). © 2022, CC BY-NC-ND.

关键词： Ultra-wideband (UWB)

来源：评论

学校读者我要写书评

暂无评论

“Only the Old and Sick Will Die” - Reproducing ‘Eugenic Visuality’ in COVID-19 Data Visualization

“Only the Old and Sick Will Die” - Reproducing ‘Eugenic V...

引用

International Symposium on technology and Society (ISTAS)

作者： Rua M. Williams Computer Graphics Technology Purdue University West Lafayette IN USA

COVID-19 illness and death has disproportionately impacted marginalized groups the world over. In the United States, Black and Indigenous people have endured the largest risk of death. Disabled and chronically ill people have continued to isolate as their peers “return to normal”, bearing sole liability for their own safety in a society that deems their lives not worth the “sacrifice” of public health measures. While public and institutional policy makers bare personal responsibility for “survival of the fittest” approaches to public health, data science and visualization has contributed to and legitimized many of these eugenic policy decisions through design tropes I characterize as ‘eugenic visuality’. In this paper, I explore how inadequacies and obscurities in COVID-19 data visualization have contributed to and sustained public narratives that devalue marginalized lives for the comfort of white-supremacist and capitalist social norms. While I focus on visualizations and statements provided by the CDC, the implications extend beyond any individual or institution to our collective preconceptions and values. Namely, unexamined biases and unquestioned norms are embedded in data science and visualization, constraining how data is represented and interpreted. These assumptions limit how data can be leveraged in the pursuit of just social policy. Therefore, I propose guiding principles for a Just Visuality in data science and representation, supported by the work of disabled activists and scholars of color.

关键词：

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：