Computer Science Research Notes最新文献_第5页

Photogrammetry Workflow for Obtaining Low-polygon 3D Models Using Free Software 使用免费软件获取低多边形3D模型的摄影测量工作流程

Computer Science Research Notes Pub Date : 2023-07-01 DOI: 10.24132/csrn.3301.42

Ricardo Pardo Romero, Inmaculada Remolar Quintana

引用次数: 0

Training Image Synthesis for Shelf Item Detection reflecting Alignments of Items in Real Image Dataset 基于实景图像数据集的货架物品检测训练图像合成

Computer Science Research Notes Pub Date : 2023-07-01 DOI: 10.24132/csrn.3301.11

Tomokazu Kaneko, Ryosuke Sakai, Soma Shiraishi

引用次数: 0

First Considerations in Computing and Using Hypersurface Curvature for Energy Efficiency 计算和使用超曲面曲率求解能量效率的首要考虑

Computer Science Research Notes Pub Date : 2023-07-01 DOI: 10.24132/csrn.3301.22

Jacob D. Hauenstein, imothy S. Newman

引用次数: 0

Synthetic-Real Domain Adaptation for Probabilistic Pose Estimation 概率姿态估计的合成实域自适应

Computer Science Research Notes Pub Date : 2023-07-01 DOI: 10.24132/csrn.3301.16

Omar Del-Tejo-Catalá, Javier Pérez, J. Guardiola, Alberto J. Perez, J. Pérez-Cortes

{"title":"Synthetic-Real Domain Adaptation for Probabilistic Pose Estimation","authors":"Omar Del-Tejo-Catalá, Javier Pérez, J. Guardiola, Alberto J. Perez, J. Pérez-Cortes","doi":"10.24132/csrn.3301.16","DOIUrl":"https://doi.org/10.24132/csrn.3301.16","url":null,"abstract":"Real samples are costly to acquire in many real-world problems. Thus, employing synthetic samples is usually the primary solution to train models that require large amounts of data. However, the difference between synthetically generated and real images, called domain gap, is the most significant hindrance to this solution, as it affects the model’s generalization capacity. Domain adaptation techniques are crucial to train models using synthetic samples. Thus, this article explores different domain adaptation techniques to perform pose estimation from a probabilistic multiview perspective. Probabilistic multiview pose estimation solves the problem of object symmetries, where a single view of an object might not be able to determine the 6D pose of an object, and it must consider its prediction as a distribution of possible candidates. GANs are currently state-of-the-art in domain adaptation. In particular, this paper explores CUT and CycleGAN, which have unique training losses that address the problem of domain adaptation from different perspectives. The datasets explored are a cylinder and a sphere extracted from a Kaggle challenge with perspective-wise symmetries, although they holistically have unique 6D poses. CUT outperforms CycleGAN in feature adaptation, although it is less robust than CycleGAN in keeping keypoints intact after translation, leading to pose prediction errors for some objects. Moreover, this paper found that training the models using synthetic-to-real images and evaluating them with real images improves the model’s accuracy for datasets without complex features. This approach is more suitable for industrial applications to reduce inference overhead.","PeriodicalId":322214,"journal":{"name":"Computer Science Research Notes","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134253304","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Low-Rank Rational Approximation of Natural Trochoid Parameterizations 自然菱形参数化的低秩有理逼近

Computer Science Research Notes Pub Date : 2023-07-01 DOI: 10.24132/csrn.3301.91

Csaba Bálint, Gábor Valasek, L. Gergó

{"title":"Low-Rank Rational Approximation of Natural Trochoid Parameterizations","authors":"Csaba Bálint, Gábor Valasek, L. Gergó","doi":"10.24132/csrn.3301.91","DOIUrl":"https://doi.org/10.24132/csrn.3301.91","url":null,"abstract":"Arc-length or natural parametrization of curves traverses the shape with unit speed, enabling uniform sampling and straightforward manipulation of functions defined on the geometry. However, Farouki and Sakkalis proved that it is impossible to parametrize a plane or space curve as a rational polynomial of its arc-length, except for the straight line. Nonetheless, it is possible to obtain approximate natural parameterizations that are exact up to any epsilon. If the given family of curves possesses a small number of scalar degrees of freedom, this results in simple approximation formulae applicable in high-performance scenarios. To demonstrate this, we consider the problem of finding the natural parametrization of ellipses and cycloids. This requires the inversion of elliptic integrals of the second kind. To this end, we formulate a two-dimensional approximation problem based on machine-epsilon exact Chebhysev proxies for the exact solutions. We also derive approximate low-rank and low-degree rational natural parametrizations via singular value decomposition. The resulting formulas have minimal memory and computational footprint, making them ideal for computer graphics applications.","PeriodicalId":322214,"journal":{"name":"Computer Science Research Notes","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116289874","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Visualization of deviations between different geometries using a multi-level voxel-based representation 使用基于体素的多层次表示来可视化不同几何形状之间的偏差

Computer Science Research Notes Pub Date : 2023-07-01 DOI: 10.24132/csrn.3301.18

Andreas Dietze, P. Grimm, Yvonne Jung

{"title":"Visualization of deviations between different geometries using a multi-level voxel-based representation","authors":"Andreas Dietze, P. Grimm, Yvonne Jung","doi":"10.24132/csrn.3301.18","DOIUrl":"https://doi.org/10.24132/csrn.3301.18","url":null,"abstract":"We present an approach for visualizing deviations between a 3d printed object and its digital twin. The corresponding 3d visualization for instance allows to highlight particularly critical sections that indicate high deviations along with corresponding annotations. Therefore, the 3d printing thus needs to be reconstructed in 3d, again. However, since the original 3d model that served as blueprint for the 3d printer typically differs topology-wise from the 3d reconstructed model, the corresponding geometries cannot simply be compared on a per-vertex basis. Thus, to be able to easily compare two topologically different geometries, we use a multi-level voxel-based representation for both data sets. Besides using different appearance properties to show deviations, a quantitative comparison of the voxel-sets based on statistical methods is added as input for the visualization. These methods are also compared to determine the best solution in terms of the shape differences and how the results differ, when comparing either voxelized volumes or hulls. The application VoxMesh integrates these concepts into an application and provides the possibility to save the results in form of voxel-sets, meshes and point clouds persistently, that can either be used by third party software or VoxMesh to efficiently reproduce and visualize the results of the shape analysis.","PeriodicalId":322214,"journal":{"name":"Computer Science Research Notes","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122693950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

3D Gaussian Descriptor for Video-based Person Re-Identification 基于视频的人物再识别三维高斯描述符

Computer Science Research Notes Pub Date : 2019-05-27 DOI: 10.24132/csrn.2019.2901.1.20

Chirine Riachy, Noor Al-Máadeed, Daniel Organisciak, F. Khelifi, A. Bouridane

{"title":"3D Gaussian Descriptor for Video-based Person Re-Identification","authors":"Chirine Riachy, Noor Al-Máadeed, Daniel Organisciak, F. Khelifi, A. Bouridane","doi":"10.24132/csrn.2019.2901.1.20","DOIUrl":"https://doi.org/10.24132/csrn.2019.2901.1.20","url":null,"abstract":"Despite being often considered less challenging than image-based person re-identification (re-id), video-based person re-id is still appealing as it mimics a more realistic scenario owing to the availability of pedestrian sequences from surveillance cameras. In order to exploit the temporal information provided, a number of feature extraction methods have been proposed. Although the features could be equally learned at a significantly higher computational cost, the scarce nature of labelled re-id datasets encourages the development of robust hand-crafted feature representations as an efficient alternative, especially when novel distance metrics or multi-shot ranking algorithms are to be validated. This paper presents a novel hand-crafted feature representation for video-based person re-id based on a 3-dimensional hierarchical Gaussian descriptor. Compared to similar approaches, the proposed descriptor (i) does not require any walking cycle extraction, hence avoiding the complexity of this task, (ii) can be easily fed into off-shelf learned distance metrics, (iii) and consistently achieves superior performance regardless of the matching method adopted. The performance of the proposed method was validated on PRID2011 and iLIDS-VID datasets outperforming similar methods on both benchmarks.","PeriodicalId":322214,"journal":{"name":"Computer Science Research Notes","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124915591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Corotated meshless implicit dynamics for deformable bodies 可变形体的旋转无网格隐式动力学

Computer Science Research Notes Pub Date : 2019-05-27 DOI: 10.24132/csrn.2019.2901.1.11

Jean-Nicolas Brunet, Vincent Magnoux, B. Ozell, S. Cotin

引用次数: 2

Tools for development of interactive web-based maps: application in healthcare 开发基于web的交互式地图的工具:在医疗保健中的应用

Computer Science Research Notes Pub Date : 2019-05-27 DOI: 10.24132/csrn.2019.2902.2.1

Matěj Karolyi, Jan Krejčí, Jakub Ščavnický, Roman Vyškovský, M. Komenda

引用次数: 5

A Deep CNN Model for Skin Cancer Detection and Classification 一种用于皮肤癌检测和分类的深度CNN模型

Computer Science Research Notes Pub Date : 1900-01-01 DOI: 10.24132/csrn.2021.3002.8

M. Junayed, N. Anjum, A. Noman, Baharul Islam

引用次数: 8