检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Pavoni, Gaia Ponchio, Federico Corsini, Massimiliano Muntoni, Alessandro Cignoni, Paolo Visual Computing Lab ISTI-CNR Pisa Italy

Fully automatic semantic segmentation of highly specific semantic classes and complex shapes may not meet the accuracy standards demanded by scientists. In such cases, human-centered AI solutions, able to assist operators while preserving human control over complex tasks, are a good trade-off to speed up image labeling while maintaining high accuracy levels. Taglab is an open-source AI-assisted software for annotating large orthoimages which takes advantage of different degrees of automation;it speeds up image annotation from scratch through assisted tools, creates custom fully automatic semantic segmentation models, and, finally, allows the quick edits of automatic predictions. Since the orthoimages analysis applies to several scientific disciplines, Taglab has been designed with a flexible labeling pipeline. We report our results in two different scenarios, marine ecology, and architectural heritage. © 2021, CC BY.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Developing and Maintaining aWeb 3D Viewer for the CH community: An evaluation of the 3dhop framework

Developing and Maintaining aWeb 3D Viewer for the CH communi...

引用

2018 Eurographics Workshop on Graphics and Cultural Heritage, GCH 2018

作者： Potenziani, M. Callieri, M. Scopigno, R. 1Visual Computing Lab ISTI CNR Pisa Italy

ISBN: (纸本)9783038680574

3DHOP (3D Heritage On-line Presenter) has been released 4 years ago, as an open-source framework for the creation of interactive visualization of 3D content on the web, aimed at the CH field. Transforming a research tool into a software product usable by the heterogeneous CH community is not a simple task and requires a significant amount of resources plus a specific design. This work presents the evolution of the 3DHOP system, and the complex relationship with its community of users, made of content creators, CH experts and general public. We will discuss the new features introduced, as well as the design and implementation strategy employed to maintain the software and make it usable by developers. We will evaluate the effectiveness of the platform by illustrating some of the applications built with 3DHOP either internally or by external users, as well as by presenting the results of a survey aimed at gathering the opinions and suggestions of the user community. © 2018 GCH 2018 - Eurographics Workshop on Graphics and Cultural Heritage. All rights reserved.

关键词： Product design

来源：评论

学校读者我要写书评

暂无评论

Soft Transparency for Point Cloud Rendering

Soft Transparency for Point Cloud Rendering

引用

29th Eurographics Symposium on Rendering - Experimental Ideas and Implementations, EGSR 2018

作者： Seemann, Patrick Palma, Gianpaolo Dellepiane, Matteo Cignoni, Paolo Goesele, Michael TU Darmstadt Germany Visual Computing Lab. ISTI CNR Pisa Italy

ISBN: (纸本)9783038680680

We propose a novel rendering framework for visualizing point data with complex structures and/or different quality of data. The point cloud can be characterized by setting a per-point scalar field associated to the aspect that differentiates the parts of the dataset (i.e. uncertainty given by local normal variation). Our rendering method uses the scalar field to render points as solid splats or semi-transparent spheres with non-uniform density to produce the final image. To that end, we derive a base model for integrating density in (intersecting) spheres for both the uniform and non-uniform setting and introduce a simple and fast approximation which yields interactive rendering speeds for millions of points. Because our method only relies on the basic OpenGL rasterization pipeline, rendering properties can be adjusted in real-time by user. The method has been tested on several datasets with different characteristics, and user studies show that a clearer understanding of the scene is possible in comparison with point splatting techniques and basic transparency rendering. © 2018 The Author(s).

关键词： Transparency

来源：评论

学校读者我要写书评

暂无评论

Automatic selection of video frames for path regularization and 3D reconstruction

Automatic selection of video frames for path regularization ...

引用

2016 Eurographics Workshop on Graphics and Cultural Heritage, GCH 2016

作者： Pavoni, G. Dellepiane, M. Callieri, M. Scopigno, R. Visual Computing Lab CNR-ISTI Pisa Italy

ISBN: (纸本)9783038680116

Video sequences can be a valuable source to document the state of objects and sites. They are easy to acquire and they usually ensure a complete coverage of the object of interest. One of their possible uses is to recover the acquisition path, or the 3D shape of the scene. This can be done by applying structure-from-motion techniques to a representative set of frames extracted from the video. This paper presents an automatic method for the extraction of a predefined number of representative frames that ensures an accurate reconstruction of the sequence path, and possibly enhances the 3D reconstruction of the scene. The automatic extraction is obtained by analyzing adjacent frames in a starting subset, and adding/removing frames so that the distance between them remains constant. This ensures the reconstruction of a regularized path and an optimized coverage of all the scene. Finally, more frames are added in the portions of the sequence when more detailed objects are framed. This ensures a better description of the sequence, and a more accurate dense reconstruction. The method is automatic, fast and independent from any assumption about the acquired object or the acquisition strategy. It was tested on a variety of different video sequences, showing that a satisfying result can be obtained regardless of the length and quality of the input. © 2016 The Author(s) Eurographics Proceedings © 2016 The Eurographics Association.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Anisotropic MatCap: Easy capture and reproduction of anisotropic materials

Anisotropic MatCap: Easy capture and reproduction of anisotr...

引用

2016 Italian Chapter Conference - Smart Tools and Apps in Computer Graphics, STAG 2016

作者： Magri, Dario Cignoni, Paolo Tarini, Marco University of Insubria Italy Visual Computing Lab ISTI CNR Italy

ISBN: (纸本)9783038680260

We propose Anisotropic MatCap, a simple data structure based on a small volumetric texture that is able to represent, under a fixed lighting, the behavior of anisotropic materials. The data structure is designed to allow fast and practical capture of real-world anisotropic materials (like for example fabrics) and to be used in real-time renderings, requiring only negligible time and texture memory overheads. The resulting technique is suited for application scenarios where digital objects must be inspected by an end user, recreating the look of an object made of a captured anisotropic material and seen under the predetermined lighting conditions. The technique proved particularly useful for garments and cloth visualization and design. © 2016 The Author(s) Eurographics Proceedings © 2016 The Eurographics Association.

关键词： Data structures

来源：评论

学校读者我要写书评

暂无评论

Generalized trackball for surfing over surfaces

Generalized trackball for surfing over surfaces

引用

2016 Italian Chapter Conference - Smart Tools and Apps in Computer Graphics, STAG 2016

作者： Malomo, Luigi Cignoni, Paolo Scopigno, Roberto Visual Computing Lab ISTI CNR Italy University of Pisa Italy

ISBN: (纸本)9783038680260

We present an efficient 3D interaction technique: generalizing the well known trackball approach, this technique unifies and blends the two common interaction mechanisms known as panning and orbiting. The approach allows to inspect a virtual object by navigating over its surrounding space, remaining at a chosen distance and performing an automatic panning over its surface. This generalized trackball allows an intuitive navigation of topologically complex shapes, enabling unexperienced users to visit hard-to-reach parts better and faster than with standard GUI components. The approach is based on the construction of multiple smooth approximations of the model under inspection;at rendering time, it constrains the camera to stay at a given distance to these approximations. The approach requires negligible preprocessing and memory overhead and works well for both mouse-based and touch interfaces. An informal user study confirms the impact of the proposed technique. © 2016 The Author(s) Eurographics Proceedings © 2016 The Eurographics Association.

关键词： Air navigation

来源：评论

学校读者我要写书评

暂无评论

Mobile reconstruction and exploration of indoor structures exploiting omnidirectional images 16

Mobile reconstruction and exploration of indoor structures e...

引用

2016 SIGGRAPH ASIA Mobile Graphics and Interactive Applications, SA 2016

作者： Pintore, Giovanni Ganovelli, Fabio Gobbetti, Enrico Scopigno, Roberto Visual Computing Group CRS4 Pula Italy Visual Computing Lab ISTI-CNR Pisa Italy

ISBN: (纸本)9781450345514

We summarize our recent advances in acquisition, reconstruction and exploration of indoor environments with the aid of mobile devices. Our methods enable casual users to quickly capture and recover multi-room structures coupled with their visual appearance, starting from panorama images generated with the built-in capabilities of modern mobile devices, as well as emerging low-cost 360° cameras. After introducing the reconstruction algorithms at the base of our approach, we show how to build applications able to generate 3D floor plans scaled to their real-world metric dimensions and capable to manage scene not necessary limited by Manhattan World assumptions. Then, exploiting the resulting structural and visual model, we propose a client-server interactive exploration system implementing a low-DOF navigation interface, specifically developed for touch interaction on smartphones and tablets.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Multi-view ambient occlusion for enhancing visualization of raw scanning data

Multi-view ambient occlusion for enhancing visualization of ...

引用

2016 Eurographics Workshop on Graphics and Cultural Heritage, GCH 2016

作者： Sabbadin, Manuele Palma, Gianpaolo Cignoni, Paolo Scopigno, Roberto Visual Computing Lab ISTI CNR Italy Department of Computer Science University of Pisa Italy

ISBN: (纸本)9783038680116

The correct understanding of the 3D shape is a crucial aspect to improve the 3D scanning process, especially in order to perform high quality and as complete as possible 3D acquisitions on the field. The paper proposes a new technique to enhance the visualization of raw scanning data based on the definition in device space of a Multi-View Ambient Occlusion (MVAO). The approach allows improving the comprehension of the 3D shape of the input geometry and, requiring almost no preprocessing, it can be directly applied to raw captured point clouds. The algorithm has been tested on different datasets: high resolution Time-of-Flight scans and streams of low quality range maps from a depth camera. The results enhance the details perception in the 3D geometry using the multi-view information to make more robust the ambient occlusion estimation. © 2016 The Author(s) Eurographics Proceedings © 2016 The Eurographics Association.

关键词： visualization

来源：评论

学校读者我要写书评

暂无评论

Automating large 3D dataset publication in a web-based multimedia repository

Automating large 3D dataset publication in a web-based multi...

引用

2016 Italian Chapter Conference - Smart Tools and Apps in Computer Graphics, STAG 2016

作者： Potenziani, M. Fritsch, B. Dellepiane, M. Scopigno, R. Visual Computing Lab ISTI CNR Pisa Italy Excellence Cluster Topoi HU Berlin Germany

ISBN: (纸本)9783038680260

Online publishing of almost every type of 3D data has become a quasi-standard routine. Nevertheless, the integration in a web page of a single 3D model, or of a predefined restricted set of models, raises different issues compared to an efficient and effective integration of thousands of them in an online repository. In this case it is mandatory to have an automatized pipeline to prepare and homogenize the dataset. The pipeline should be able to automatically wrap 3D data in all conditions, and display every single model with the best scene setup without any (or with a minimal) interaction by the database maintainers. This paper, retracing the steps of a recent real application case, aims at showing all the faced issues (and the adopted solutions) to publish a large and heterogeneous three-dimensional dataset in a web specialized repository. We want to introduce a valid and reusable strategy, starting from the description of the pipeline adopted for data pre-processing and moving to the choices made in the 3D viewer implementation. The paper concludes with a discussion on the actual state of the integration of 3D data with the other multimedia informative layers. © 2016 The Author(s) Eurographics Proceedings © 2016 The Eurographics Association.

关键词： Integration

来源：评论

学校读者我要写书评

暂无评论

Book review 3D Recording, Documentation and Management of Cultural Heritage , E. Stylianidis , F. Remondino (Eds.) , Whittles Publishing , Scotland, UK ( 2016 ) , 388 pp., full color, ISBN: 9781849951685

引用

Journal of Cultural Heritage 2017年 23卷 185-185页

作者： Marco Callieri Visual Computing Lab ISTI-CNR Pisa Italy

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：