检索结果-南通市图书馆

On the role of geometry in geo-localization

Computational Visual Media 2021年第1期7卷 103-113页

作者： Moti Kadosh Yael Moses ariel shamir Department of Electrical Engineering Tel-Aviv UniversityTel-AvivIsrael The Efi Arazi School of Computer Science The Interdisciplinary Center HerzliyaHerzliyaIsrael

Consider the geo-localization task of finding the pose of a camera in a large 3 D scene from a single *** existing CNN-based methods use as input textured *** aim to experimentally explore whether texture and correlation between nearby images are necessary in a CNN-based solution for the geo-localization *** do so,we consider lean images,textureless projections of a simple 3 D model of a *** only contain information related to the geometry of the scene viewed(edges,faces,and relative depth).The main contributions of this paper are:(i)to demonstrate the ability of CNNs to recover camera pose using lean images;and(ii)to provide insight into the role of geometry in the CNN learning process.

关键词： geo-localization geometry CNN-based solutions synthetic lean images

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Image resizing by reconstruction from deep features

引用

Computational Visual Media 2021年第4期7卷 453-466页

作者： Dov Danon Moab Arar Daniel Cohen-Or ariel shamir Tel Aviv University Tel Aviv69978Israel The Interdisciplinary Center Herzliya Herzliya4610101

Traditional image resizing methods usually work in pixel space and use various saliency *** challenge is to adjust the image shape while trying to preserve important *** this paper we perform image resizing in feature space using the deep layers of a neural network containing rich important semantic *** directly adjust the image feature maps,extracted from a pre-trained classification network,and reconstruct the resized image using neuralnetwork based *** novel approach leverages the hierarchical encoding of the network,and in particular,the high-level discriminative power of its deeper layers,that can recognize semantic regions and objects,thereby allowing maintenance of their aspect *** use of reconstruction from deep features results in less noticeable artifacts than use of imagespace resizing *** evaluate our method on benchmarks,compare it to alternative approaches,and demonstrate its strengths on challenging images.

关键词： image retargeting reconstruction deep seam carving image resizing

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

NPRportrait 1.0:A three-level benchmark for non-photorealistic rendering of portraits

引用

Computational Visual Media 2022年第3期8卷 445-465页

作者： Paul L.Rosin Yu-Kun Lai David Mould Ran Yi Itamar Berger Lars Doyle Seungyong Lee Chuan Li Yong-Jin Liu Amir Semmo ariel shamir Minjung Son Holger Winnemöller School of Computer Science and Informatics Cardiff UniversityCardiffUK School of Computer Science Carleton UniversityOttawaCanada Department of Computer Science and Technology Tsinghua UniversityBeijingChina Reichman University(the Interdisciplinary Center) HerzliyaIsrael Department of Computer Science and Engineering Pohang University of Science and TechnologyPohangRepublic of Korea Lambda Labs Inc.San FranciscoUSA Hasso Plattner Institute University of PotsdamPotsdamGermany Multimedia Processing Laboratory Samsung Advanced Institute of TechnologySuwonRepublic of Korea Adobe Systems Inc.San JoseUSA

Recently,there has been an upsurge of activity in image-based non-photorealistic rendering(NPR),and in particular portrait image stylisation,due to the advent of neural style transfer(NST).However,the state of performance evaluation in this field is poor,especially compared to the norms in the computer vision and machine learning ***,the task of evaluating image stylisation is thus far not well defined,since it involves subjective,perceptual,and aesthetic *** make progress towards a solution,this paper proposes a new structured,threelevel,benchmark dataset for the evaluation of stylised portrait *** criteria were used for its construction,and its consistency was validated by user ***,a new methodology has been developed for evaluating portrait stylisation algorithms,which makes use of the different benchmark levels as well as annotations provided by user studies regarding the characteristics of the *** perform evaluation for a wide variety of image stylisation methods(both portrait-specific and general purpose,and also both traditional NPR approaches and NST)using the new benchmark dataset.

关键词： non-photorealistic rendering(NPR) image stylization style transfer portrait evaluation benchmark

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Preface

引用

Journal of Computer Science & Technology 2018年第3期33卷 429-430页

作者： Shi-Min Hu Ce-Wu Lu ariel shamir Department of Computer Science and Technology Tsinghua University Beijing China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Efi Arazi School of Computer Science Interdisciplinary Center Herzliya Israel

The Computational Visual Media （CVM） conference series is intended to provide a major international forum for exchanging novel research ideas and significant computational methods that either underpin or apply visual media. The primary goal is to promote cross-disciplinary research to amalgamate aspects of computer graphics, computer vision, machine learning, image and video processing, visualization and geometric computing. The main topics of interest to CVM include classification, composition, retrieval, synthesis, cognition and understanding of visual media （e.g., images, video, 3D geometry）.

关键词：

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

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：