检索结果-内蒙古大学图书馆

32nd International Conference in Central Europe on computer graphics, Visualization and computer vision, WSCG 2024

作者： Gamillscheg, Florian Ruprecht, Irena Settgast, Volker Pietroszek, Krzysztof Augsdörfer, Ursula Institute of Computer Graphics and Knowledge Visualisation Graz University of Technology Austria Fraunhofer Austria Graz Austria American University WashingtonDC United States Graz University of Technology Austria

Virtual Reality (VR) applications constantly strive for more realism, immersion and intuitive user experiences. Traditional VR controllers can hinder full immersion, since they form an additional barrier between the user’s thoughts or intentions and the virtual world. Brain computer interfaces (BCIs) have the potential to close this gap by enabling an immediate translation of human thoughts to commands that can be processed by a computer. This paper investigates the feasibility of employing an affordable commercial BCI device for VR interaction. In a preliminary study conducted in a Cave Automatic Virtual Environment (CAVE), we evaluate both the effectiveness and limitations of the popular BCI device Emotiv Insight. © 2024 university of West Bohemia. All rights reserved.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

TAEC: Unsupervised action segmentation with temporal-Aware embedding and clustering 26

TAEC: Unsupervised action segmentation with temporal-Aware e...

引用

26th computer vision Winter Workshop, CVWW 2023

作者： Lin, Wei Kukleva, Anna Possegger, Horst Kuehne, Hilde Bischof, Horst Institute of Computer Graphics and Vision Graz University of Technology Austria Christian Doppler Laboratory for Semantic 3D Computer Vision Austria Max-Planck-Institute for Informatics Germany Goethe University Frankfurt Germany

Temporal action segmentation in untrimmed videos has gained increased attention recently. However, annotating action classes and frame-wise boundaries is extremely time consuming and cost intensive, especially on large-scale datasets. To address this issue, we propose an unsupervised approach for learning action classes from untrimmed video sequences. In particular, we propose a temporal embedding network that combines relative time prediction, feature reconstruction, and sequence-To-sequence learning, to preserve the spatial layout and sequential nature of the video features. A two-step clustering pipeline on these embedded feature representations then allows us to enforce temporal consistency within, as well as across videos. Based on the identified clusters, we decode the video into coherent temporal segments that correspond to semantically meaningful action classes. Our evaluation on three challenging datasets shows the impact of each component and, furthermore, demonstrates our state-of-The-Art unsupervised action segmentation results. © 2023 Copyright for this paper by its authors.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Learned Discretization Schemes for the Second-Order Total Generalized Variation 9th

Learned Discretization Schemes for the Second-Order Total ...

引用

9th International Conference on Scale Space and Variational Methods in computer vision, SSVM 2023

作者： Bogensperger, Lea Chambolle, Antonin Effland, Alexander Pock, Thomas Institute of Computer Graphics and Vision Graz University of Technology Graz Austria CEREMADE CNRS & Université Paris-Dauphine PSL Paris France Institute for Applied Mathematics University of Bonn Bonn Germany

ISBN: (纸本)9783031319747

The total generalized variation extends the total variation by incorporating higher-order smoothness. Thus, it can also suffer from similar discretization issues related to isotropy. Inspired by the success of novel discretization schemes of the total variation, there has been recent work to improve the second-order total generalized variation discretization, based on the same design idea. In this work, we propose to extend this to a general discretization scheme based on interpolation filters, for which we prove variational consistency. We then describe how to learn these interpolation filters to optimize the discretization for various imaging applications. We illustrate the performance of the method on a synthetic data set as well as for natural image denoising. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

DEEP LEARNING-BASED POINT CLOUD REGISTRATION FOR AUGMENTED REALITY-GUIDED SURGERY

arXiv

引用

arXiv 2024年

作者： Weber, Maximilian Wild, Daniel Kleesiek, Jens Egger, Jan Gsaxner, Christina Institute of Computer Graphics and Vision Graz University of Technology Austria Germany

Point cloud registration aligns 3D point clouds using spatial transformations. It is an important task in computer vision, with applications in areas such as augmented reality (AR) and medical imaging. This work explores the intersection of two research trends: the integration of AR into image-guided surgery and the use of deep learning for point cloud registration. The main objective is to evaluate the feasibility of applying deep learning-based point cloud registration methods for image-to-patient registration in augmented reality-guided surgery. We created a dataset of point clouds from medical imaging and corresponding point clouds captured with a popular AR device, the HoloLens 2. We evaluate three well-established deep learning models in registering these data pairs. While we find that some deep learning methods show promise, we show that a conventional registration pipeline still outperforms them on our challenging dataset. Copyright © 2024, The Authors. All rights reserved.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

SAda-Net: A Self-Supervised Adaptive Stereo Estimation CNN For Remote Sensing Image Data

arXiv

引用

arXiv 2024年

作者： Hirner, Dominik Fraundorfer, Friedrich Graz University of Technology Institute of Computer Graphics and Vision Austria Germany

Stereo estimation has made many advancements in recent years with the introduction of deep-learning. However the traditional supervised approach to deep-learning requires the creation of accurate and plentiful ground-truth data, which is expensive to create and not available in many situations. This is especially true for remote sensing applications, where there is an excess of available data without proper ground truth. To tackle this problem, we propose a self-supervised CNN with self-improving adaptive abilities. In the first iteration, the created disparity map is inaccurate and noisy. Leveraging the left-right consistency check, we get a sparse but more accurate disparity map which is used as an initial pseudo ground-truth. This pseudo ground-truth is then adapted and updated after every epoch in the training step of the network. We use the sum of inconsistent points in order to track the network convergence. The code for our method is publicly available at: https://***/thedodo/SAda-Net © 2024, CC BY.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Towards Crowd-Sourced Collaborative Fragment Matching

Towards Crowd-Sourced Collaborative Fragment Matching

引用

2023 Eurographics Workshop on graphics and Cultural Heritage, GCH 2023

作者： Houska, P. Kloiber, S. Masur, A. Lengauer, S. Karl, S. Preiner, R. Graz University of Technology Institute of Computer Graphics and Knowledge Visualization Austria University of Graz Institute of Classics Austria

ISBN: (纸本)9783038682172

Many artifacts of our archaeological heritage are preserved only in fragments. The reassembly of these parts to their original form is therefore an essential task for archaeologists. Our project aims at incorporating the intellect of many participants from the broad public in the solution of this complex task. To this end, we develop a web-based 3D environment, in which users can interactively and collaboratively reassemble virtual fragments of real-world artifacts, supported by computer-aided methods. Our primary research focus lies on identifying how to best design and setup such a system in order to maximize the collaboration efficiency. By participating in this open reassembly process, users can gain valuable insight into the archaeological task, thus raising awareness for our common cultural heritage in a multitude of people. © ISVR,2023 *** rights reserved

关键词：

来源：评论

学校读者我要写书评

暂无评论

GAFAR: Graph-Attention Feature-Augmentation for Registration A Fast and Light-weight Point Set Registration Algorithm

GAFAR: Graph-Attention Feature-Augmentation for Registration...

引用

European Conference on Mobile Robots (ECMR)

作者： Ludwig Mohr Ismail Geles Friedrich Fraundorfer Institute of Computer Graphics and Vision Graz University of Technology Graz Austria

Rigid registration of point clouds is a fundamental problem in computer vision with many applications from 3D scene reconstruction to geometry capture and robotics. If a suitable initial registration is available, conventional methods like ICP and its many variants can provide adequate solutions. In absence of a suitable initialization and in the presence of a high outlier rate or in the case of small overlap though the task of rigid registration still presents great challenges. The advent of deep learning in computer vision has brought new drive to research on this topic, since it provides the possibility to learn expressive feature-representations and provide one-shot estimates instead of depending on time-consuming iterations of conventional robust methods. Yet, the rotation and permutation invariant nature of point clouds poses its own challenges to deep learning, resulting in loss of performance and low generalization capability due to sensitivity to outliers and characteristics of 3D scans not present during network training. In this work, we present a novel fast and light-weight network architecture using the attention mechanism to augment point descriptors at inference time to optimally suit the registration task of the specific point clouds it is presented with. Employing a fully-connected graph both within and between point clouds lets the network reason about the importance and reliability of points for registration, making our approach robust to outliers, low overlap and unseen data. We test the performance of our registration algorithm on different registration and generalization tasks and provide information on runtime and resource consumption. The code and trained weights are available at https://***/mordecaimalignatius/GAFAR/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Cross-Polarization as a Possible Cause for Color Shift in Illumination 28

A Cross-Polarization as a Possible Cause for Color Shift in ...

引用

IS and T International Symposium on Electronic Imaging: 28th Color Imaging: Displaying, Processing, Hardcopy, and Applications, COLOR 2023

作者： Haila, Tarek Abu Tausch, Reimar Ritz, Martin Santos, Pedro Fellner, Dieter W. Fraunhofer Institute for Computer Graphics Research IGD Germany Darmstadt University of Technology Germany Graz University of Technology Austria

Despite that a cross-polarization is a very efficient way to remove undesired reflections and specularities while imaging and digitizing certain type of materials. It does not come, however, with no risk when color fidelity and accuracy are of importance. This paper shows that a cross-polarization could alter and shift the Chroma component of a light source (D50) by different factors, undoubtedly, depending on the polarization filters' quality in-use. Statistics show a color difference, DE00, of at least 3.59 and at worst 7.34 when a cross-polarization is in-place compared to non-polarized settings. That corresponds to a shift in color correlated temperature ranging from 50K to 360K consequently. © 2023, Society for Imaging Science and technology.

关键词： Light sources

来源：评论

学校读者我要写书评

暂无评论

Identifying and Extracting Pedestrian Behavior in Critical Traffic Situations

arXiv

引用

arXiv 2024年

作者： Schachner, Martin Schneider, Bernd Weissenbacher, Fabian Kirillova, Nadezda Possegger, Horst Bischof, Horst Klug, Corina Vehicle Safety Institute Graz University of Technology Graz8010 Austria Institute of Computer Graphics and Vision Graz University of Technology Graz8010 Austria

A better understanding of interactive pedestrian behavior in critical traffic situations is essential for the development of enhanced pedestrian safety systems. Real-world traffic observations play a decisive role in this, since they represent behavior in an unbiased way. In this work, we present an approach of how a subset of very considerable pedestrian-vehicle interactions can be derived from a camera-based observation system. For this purpose, we have examined road user trajectories automatically for establishing temporal and spatial relationships, using 110h hours of video recordings. In order to identify critical interactions, our approach combines the metric post-encroachment time with a newly introduced motion adaption metric. From more than 11,000 reconstructed pedestrian trajectories, 259 potential scenarios remained, using a post-encroachment time threshold of 2s. However, in 95% of cases, no adaptation of the pedestrian behavior was observed due to avoiding criticality. Applying the proposed motion adaption metric, only 21 critical scenarios remained. Manual investigations revealed that critical pedestrian vehicle interactions were present in 7 of those. They were further analyzed and made publicly available for developing pedestrian behavior models3. The results indicate that critical interactions in which the pedestrian perceives and reacts to the vehicle at a relatively late stage can be extracted using the proposed method. © 2024, CC BY-NC-ND.

关键词： Pedestrian safety

来源：评论

学校读者我要写书评

暂无评论

ATS: Adaptive Temperature Scaling for Enhancing Out-of-Distribution Detection Methods

ATS: Adaptive Temperature Scaling for Enhancing Out-of-Distr...

引用

IEEE Workshop on Applications of computer vision (WACV)

作者： Gerhard Krumpl Henning Avenhaus Horst Possegger Horst Bischof Institute of Computer Graphics and Vision Graz University of Technology Austria KESTRELEYE GmbH Austria

Out-of-distribution (OOD) detection is essential to ensure the reliability and robustness of machine learning models in real-world applications. Post-hoc OOD detection methods have gained significant attention due to the fact that they offer the advantage of not requiring additional re-training, which could degrade model performance and increase training time. However, most existing post-hoc methods rely only on the encoder output (features), logits, or the softmax probability, meaning they have no access to information that might be lost in the feature extraction process. In this work, we address this limitation by introducing Adaptive Temperature Scaling (ATS), a novel approach that dynamically calculates a temperature value based on activations of the intermediate layers. Fusing this sample-specific adjustment with class-dependent logits, our ATS captures additional statistical information before they are lost in the feature extraction process, leading to a more robust and powerful OOD detection method. We conduct extensive experiments to demonstrate the efficacy of our approach. Notably, our method can be seamlessly combined with SOTA post-hoc OOD detection methods that rely on the logits, thereby enhancing their performance and improving their robustness.

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：