PFI:AIR - TT: A System for 3D Content-based Data Management

这个PFI：AIR技术翻译项目专注于翻译三维(3D)内容管理技术，以满足对能够处理3D内容和支持3D制造扩展的系统的需求。这种基于3D内容的数据管理系统很重要，因为它对3D打印和制造业的信息支持产生了影响。3D制造业在管理网络规模的3D内容方面面临着越来越大的挑战，而管理3D存储库的进展仍处于早期阶段。因此，能够管理大规模3D内容的系统在培育更容易访问的3D内容市场方面发挥了关键作用，并为内容创作者和消费者提供了新的就业和收入机会(例如，通过降低初创公司将新产品推向市场的障碍)。该项目将产生一个具有以下独特功能的网络规模系统的概念验证：对象浏览、查询处理和3D对象合成/分解机制的交互。这些功能提供了基于微服务模型实现复杂应用的优势，这是该市场领域的一种新架构。该项目解决了3D信息管理从研究发现向商业应用转化的几个技术差距。具体地说，它包括计算方法，例如基于多对多匹配算法的相似性测量，该算法与3D对象的体积表示一起工作，并在两个对象及其部分之间产生可用于配准和并置的直接对应。它还将过渡几种已开发的机制，用于索引3D对象的基于零件的表示法，进而可用于从模型数据库中高效地检索候选对象。我们提出的3D零件的部分匹配将利用3D曲面水平集的一种新的变形，该变形提供了两个曲面之间的形状相似性度量。这一度量将允许我们执行广义曲面的高精度匹配。此外，参与该项目的人员，包括四名高级(初级或高级)本科生，将通过接触真实世界的软件工程流程、信息检索和大型数据管理工具获得创业和技术翻译经验。这一经历将提供技能、知识和经验，为学生在学术生涯或工业就业做好准备。该项目与3D Industries(3DI)Ltd.合作，以确保Drexel团队？S在该项目下的翻译研究工作保持在正轨上，以解决关键的商业需求，并将上市时间降至最低。3DI的参与将增加德雷克塞尔团队S的研究努力，同时也为德雷克塞尔团队创造机会，快速接收和适应来自实际工作用户的反馈。

This PFI:AIR Technology Translation project focuses on translating 3-Dimensional (3D) content management technology to fill the need for systems that are capable of processing 3D content and sustaining expansion of 3D manufacturing. This 3D Content-based data management system is important because of its impact on information support for the 3D printing and manufacturing industry. The 3D manufacturing industry is facing a growing challenge in managing web-scale 3D content and the progress in managing 3D repositories is still in its early stages. As a result, systems that are capable of managing large-scale 3D content play a critical role in fostering a market for 3D content that is more accessible and offers the potential for new job and income opportunities for both content creators and consumers (e.g. by reducing the barrier for a startup to bring a new product to market). The project will result in a proof-of-concept of a web-scale system with the following unique features: object browsing, query processing, and interaction of 3D object composition/decomposition mechanisms. These features provide the advantages of an implementation based on a micro-services model for complex applications, which is a new architecture in this market space.This project addresses several technology gaps in 3D information management as it translates from research discovery toward commercial application. Specifically, it includes computational methods such as similarity measurements based on a many-to-many matching algorithm that work with volumetric representations of 3D objects and produce a direct correspondence between two objects and their parts, which can be used for registration and juxtaposition. It will also transition several developed mechanisms for indexing a part-based representation of 3D objects, which in turn can be used for efficient retrieval of candidates from a database of models. Our proposal for partial matching of 3D parts will utilize a novel morphing of level sets of 3D surfaces that provides a shape similarity metric between the two surfaces. This metric will allow us to perform high accuracy matching of generalized surfaces. In addition, personnel involved in this project, including four upper-level (junior or senior) undergraduates, will receive entrepreneurship and technology translation experience through exposure to real-world software engineering processes, information retrieval, and large-scale data management tools. This experience will provide the skills, knowledge and experience to prepare the students for either academic careers or employment in industry. The project engages 3D Industries (3DI) Ltd. to ensure the Drexel team?s translational research efforts under the project remain on track to solve critical commercial needs and to minimize the time to market. 3DI's participation will augment the Drexel team?s research efforts while also creating the opportunity for the Drexel team to quickly receive and adapt to feedback from real-work users.