检索结果-内蒙古大学图书馆

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 Cost-Effective Approach to Smooth A* Path Planning for Autonomous Vehicles

A Cost-Effective Approach to Smooth A* Path Planning for Aut...

引用

Automated Vehicle Validation Conference (IAVVC), IEEE International

作者： Lukas Schichler Karin Festl Selim Solmaz Daniel Watzenig Virtual Vehicle Research GmbH Graz Austria Institute of Computer Graphics and Vision TU Graz

ISBN: (数字)9798350354072

ISBN: (纸本)9798350354089

Path planning for wheeled mobile robots is a critical component in the field of automation and intelligent transportation systems. Car-like vehicles, which have non-holonomic constraints on their movement capability impose additional requirements on the planned paths. Traditional path planning algorithms, such as A * , are widely used due to their simplicity and effectiveness in finding optimal paths in complex environments. However, these algorithms often do not consider vehicle dynamics, resulting in paths that are infeasible or impractical for actual driving. Specifically, a path that minimizes the number of grid cells may still be too curvy or sharp for a car-like vehicle to navigate *** paper addresses the need for a path planning solution that not only finds a feasible path but also ensures that the path is smooth and drivable. By adapting the A * algorithm for a curvature constraint and incorporating a cost function that considers the smoothness of possible paths, we aim to bridge the gap between grid based path planning and smooth paths that are drivable by car-like vehicles. The proposed method leverages motion primitives, pre-computed using a ribbon based path planner that produces smooth paths of minimum curvature. The motion primitives guide the A * algorithm in finding paths that are optimal in terms of both length and curvature. With the proposed modification on the A * algorithm, the planned paths can be constraint to have a minimum turning radius much larger than the grid size. We demonstrate the effectiveness of the proposed path planning algorithm in different unstructured environments. In a two-stage planning approach, first the modified A * algorithm finds a grid-based path and the ribbon based path planner creates a smooth path within the area of grid cells. The resulting paths are smooth with small curvatures independent of the orientation of the grid axes and even in presence of sharp obstacles.

关键词： Automation Navigation Heuristic algorithms Cost function Turning Path planning Planning Mobile robots Vehicle dynamics Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

FLOWSDF: FLOW MATCHING FOR MEDICAL IMAGE SEGMENTATION USING DISTANCE TRANSFORMS

arXiv

引用

arXiv 2024年

作者： Bogensperger, Lea Narnhofer, Dominik Falk, Alexander Schindler, Konrad Pock, Thomas Institute of Computer Graphics and Vision Graz University of Technology Graz Austria Photogrammetry and Remote Sensing ETH Zurich Zurich Switzerland Institute of Computer Graphics and Vision Graz University of Technology Austria Photogrammetry and Remote Sensing ETH Zurich Switzerland

Medical image segmentation plays an important role in accurately identifying and isolating regions of interest within medical images. Generative approaches are particularly effective in modeling the statistical properties of segmentation masks that are closely related to the respective structures. In this work we introduce FlowSDF, an image-guided conditional flow matching framework, designed to represent the signed distance function (SDF), and, in turn, to represent an implicit distribution of segmentation masks. The advantage of leveraging the SDF is a more natural distortion when compared to that of binary masks. Through the learning of a vector field associated with the probability path of conditional SDF distributions, our framework enables accurate sampling of segmentation masks and the computation of relevant statistical measures. This probabilistic approach also facilitates the generation of uncertainty maps represented by the variance, thereby supporting enhanced robustness in prediction and further analysis. We qualitatively and quantitatively illustrate competitive performance of the proposed method on a public nuclei and gland segmentation data set, highlighting its utility in medical image segmentation applications. © 2024, CC BY.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A Cost-Effective Approach to Smooth A* Path Planning for Autonomous Vehicles

arXiv

引用

arXiv 2024年

作者： Schichler, Lukas Festl, Karin Solmaz, Selim Watzenig, Daniel Virtual Vehicle Research GmbH Graz Austria Institute of Computer Graphics and Vision TU Graz Austria

component Abstract—Path in the planning field of for automation wheeled mobile and _ robots intelligent is a critical transportation systems. Car-like vehicles, which have non-holonomic constraints on their movement capability impose additional requirements on the planned paths. Traditional path planning algorithms, such as A*, are widely used due to their simplicity and effectiveness in finding optimal paths in complex environments. However, these algorithms often do not consider vehicle grid actual dynamics,cells driving. mayresulting Specifically, stillinbepathstoo curvy a that path areor that infeasiblesharp minimizes forora car-likeimpractical the number vehiclefor of that pathtoa curvatureThis navigate not is smoothpaper only *** finds and drivable. a feasible andtheincorporatingneedBy path adaptingfor but a path also the a costplanningA* ensures algorithm function that solutionthat the for considers the smoothness of possible paths, we aim to bridge the gap between grid based path planning and smooth paths that motion are drivable primitives, by car-like pre-computed vehicles. The using proposed a ribbon method based leverages pathplanner motion primitives that produces guide smooth the A* paths algorithm of minimum in finding curvature. paths that The are optimal in terms of both length and curvature. With the proposed modification constraint to on have the a minimum A"algorithm, turning the radius planned much paths larger can than be the grid size. We demonstrate the effectiveness of the proposed In findspatha smooth a two-stage planninga grid-based path planning algorithmwithin path the and approach, inarea thedifferentribbon of first gridunstructuredbased the cells. modified path The planner resultingenvironments. A* algorithm creates paths are smooth with small curvatures independent of the orientation of the grid axes and even in presence of sharp obstacles. Copyright © 2024, The Authors. All rights reserved.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Single Image LDR to HDR Conversion Using Conditional Diffusion

Single Image LDR to HDR Conversion Using Conditional Diffusi...

引用

IEEE International Conference on Image Processing

作者： Dwip Dalal Gautam Vashishtha Prajwal Singh Shanmuganathan Raman Computer Vision Imaging and Graphics Lab Indian Institute of Technology Gandhinagar India

Digital imaging aims to replicate realistic scenes, but Low Dynamic Range (LDR) cameras cannot represent the wide dynamic range of real scenes, resulting in under-/overexposed images. This paper presents a deep learning-based approach for recovering intricate details from shadows and highlights while reconstructing High Dynamic Range (HDR) images. We formulate the problem as an image-to-image (I2I) translation task and propose a conditional Denoising Diffusion Probabilistic Model (DDPM) based framework using classifier-free guidance. We incorporate a deep CNN-based autoencoder in our proposed framework to enhance the quality of the latent representation of the input LDR image used for conditioning. Moreover, we introduce a new loss function for LDR-HDR translation tasks, termed Exposure Loss. This loss helps direct gradients in the opposite direction of the saturation, further improving the results’ quality. By conducting comprehensive quantitative and qualitative experiments, we have effectively demonstrated the proficiency of our proposed method. The results indicate that a simple conditional diffusion-based method can replace the complex camera pipeline-based architectures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Single Image LDR to HDR Conversion using Conditional Diffusion

arXiv

引用

arXiv 2023年

作者： Dalal, Dwip Vashishtha, Gautam Singh, Prajwal Raman, Shanmuganathan Computer Vision Imaging and Graphics Lab Indian Institute of Technology Gandhinagar India

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

InfoSeg: Unsupervised Semantic Image Segmentation with Mutual Information Maximization 43rd

InfoSeg: Unsupervised Semantic Image Segmentation with Mutua...

引用

43rd DAGM German Conference on Pattern Recognition, DAGM GCPR 2021

作者： Harb, Robert Knöbelreiter, Patrick Institute of Computer Graphics and Vision Graz University of Technology Graz Austria

ISBN: (纸本)9783030926588

We propose a novel method for unsupervised semantic image segmentation based on mutual information maximization between local and global high-level image features. The core idea of our work is to leverage recent progress in self-supervised image representation learning. Representation learning methods compute a single high-level feature capturing an entire image. In contrast, we compute multiple high-level features, each capturing image segments of one particular semantic class. To this end, we propose a novel two-step learning procedure comprising a segmentation and a mutual information maximization step. In the first step, we segment images based on local and global features. In the second step, we maximize the mutual information between local features and high-level features of their respective class. For training, we provide solely unlabeled images and start from random network initialization. For quantitative and qualitative evaluation, we use established benchmarks, and COCO-Persons, whereby we introduce the latter in this paper as a challenging novel benchmark. InfoSeg significantly outperforms the current state-of-the-art, e.g., we achieve a relative increase of 26 % in the Pixel Accuracy metric on the COCO-Stuff dataset. © 2021, Springer Nature Switzerland AG.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Filtering Decision Rules Driven by Sequential Forward and Backward Selection of Attributes: An Illustrative Example in Stylometric Domain 18

Filtering Decision Rules Driven by Sequential Forward and Ba...

引用

18th Conference on computer Science and Intelligence Systems, FedCSIS 2023

作者： Zielosko, Beata Stanczyk, Urszula Jablonski, Kamil Institute of Computer Science University of Silesia in Katowice Bedzínska 39 Sosnowiec41-200 Poland Department of Graphics Silesian University of Technology Computer Vision and Digital Systems Akademicka 2A Gliwice44-100 Poland

ISBN: (纸本)9788396744784

The paper presents investigations concerning the decision rule filtering process controlled by the estimated relevance of available attributes. In the conducted study, two search directions were used, sequential forward selection and sequential backward elimination. The steps of sequential search were governed by three rankings obtained for variables, all related to characteristics of data and rules that can be induced, as follows, (i) a ranking based on the weighting factor referring to the occurrence of attributes in generated decision reducts, (ii) the OneR ranking exploiting short rule properties, and (iii) the proposed ranking defined through the operation of greedy algorithm for rule induction. The three rankings were confronted and compared from the perspective of their usefulness for the selection of rules performed in the two directions and with two strategies for rule selection. The resulting sets of rules were analysed with respect to the properties of the constituent decision rules and from the point of performance for all constructed rule-based classifiers. Substantial experiments were carried out in the stylometric domain, treating the task of authorship attribution as classification. The results obtained indicate that for all three rankings and search paths it was possible to obtain a noticeable reduction of attributes while at least maintaining the power of inducers, at the same time improving characteristics of rule sets. © 2023 Polish Information Processing Society.

关键词： Information use

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

Deep Learning-Based Point Cloud Registration for Augmented R...

引用

IEEE International Symposium on Biomedical Imaging

作者： Maximilian Weber Daniel Wild Jens Kleesiek Jan Egger Christina Gsaxner Institute of Computer Graphics and Vision Graz University of Technology Institute for Artificial Intelligence in Medicine University Hospital Essen (AöR)

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

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.

关键词： Point cloud compression Deep learning Accuracy Three-dimensional displays Noise Surgery Registers

来源：评论

学校读者我要写书评

暂无评论

LaFTer: label-free tuning of zero-shot classifier using language and unlabeled image collections 23

LaFTer: label-free tuning of zero-shot classifier using lang...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： M. Jehanzeb Mirza Leonid Karlinsky Wei Lin Mateusz Kozinski Horst Possegger Rogerio Feris Horst Bischof Institute of Computer Graphics and Vision TU Graz Austria and Christian Doppler Laboratory for Embedded Machine Learning MIT-IBM Watson AI Lab Institute of Computer Graphics and Vision TU Graz Austria

Recently, large-scale pre-trained vision and Language (VL) models have set a new state-of-the-art (SOTA) in zero-shot visual classification enabling open-vocabulary recognition of potentially unlimited set of categories defined as simple language prompts. However, despite these great advances, the performance of these zero-shot classifiers still falls short of the results of dedicated (closed category set) classifiers trained with supervised fine-tuning. In this paper we show, for the first time, how to reduce this gap without any labels and without any paired VL data, using an unlabeled image collection and a set of texts auto-generated using a Large Language Model (LLM) describing the categories of interest and effectively substituting labeled visual instances of those categories. Using our label-free approach, we are able to attain significant performance improvements over the zero-shot performance of the base VL model and other contemporary methods and baselines on a wide variety of datasets, demonstrating absolute improvement of up to 11.7% (3.8% on average) in the label-free setting. Moreover, despite our approach being label-free, we observe 1.3% average gains over leading few-shot prompting baselines that do use 5-shot supervision.

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：