Google 3D Warehouse Research Articles

Learned 3D shape descriptors for classifying 3D point cloud models

ABSTRACTRecent hardware advances in the field of 3D imaging are democratizing 3D sensing with tremendous scientific and societal implications. Point cloud processing has traditionally required meshing the point clouds output by 3D cameras followed by surface reconstruction, and geometric feature recognition. However, meshing a point cloud is fundamentally an ill-posed problem, and the definition of a good solution is not general. This, in turn, demands new paradigms for processing point cloud information.In this paper, we focus on the task of classifying 3D point clouds captured with commercial 3D cameras, and we integrate supervised machine learning algorithms with three different yet underexplored shape descriptors, namely Light-Field Descriptors, Angular Radial Transform (ART), and Zernike Descriptors (ZD). We evaluate the classification performance of different machine learning algorithms combined with these different shape descriptors on point cloud models obtained from the Google 3D Warehouse, and w...

A wireframe model-based method for automated internal design

This paper proposes a wireframe model-based method for automated internal design. The method is used to extract geometric structure of an internal wireframe model and find out all loop structures of furniture models. The wireframe models are classified as the multiple independent sub-models according to the geometric structure by statistical analysis. The corresponding models are selected from a 3D model database to build an internal scene based on characteristic points of furniture wireframe models. In the experiments 3D database via manually selected 268 3D furniture models from Google 3D warehouse is built up. The experiments show that the method can construct 3D scenes in 1.1×103 ms. This method costs less time compared with traditional hierarchical method and depth-sensing camera method in the same experimental conditions. The method can be also used for 3D visualization either with complex backgrounds.

Joint shape and color descriptors for 3D urban model retrieval

ABSTRACTWith the rapid development of photogrammetry, computer vision and three-dimensional (3D) modeling technologies, it is possible to efficiently construct detailed 3D urban models. Accordingly, large corpora of 3D models, such as the Google 3D Warehouse, are now becoming freely available on the web. How to find the proper 3D urban models is a challenging research issue. In this paper, we join shape descriptors and color descriptors for 3D urban model retrieval. The query objects are localized and segmented automatically from the input images by using a new selective search voting algorithm. Through combining the normalization with the light field descriptor, the Horizontal Light Descriptor is introduced to measure the shape similarity among the normalized urban models. The color descriptors are used to represent the color information of the urban models. The two types of descriptors are joined to search 3D urban models similar to the query objects. Experimental results have shown the effectiveness of our approach.

Developing a 3D Game Design Authoring Package to Assist Students’ Visualization Process in Design Thinking

The teaching of 3D digital game design requires the development of students’ meta-skills, from story creativity to 3D model construction, and even the visualization process in design thinking. The characteristics a good game designer should possess have been identified as including redesign things, creativity thinking and the ability to visualize ideas from imagination. Therefore, 3D visualization is a key skill in this context. To help students fully focus on game design rather than on complicated 3D modeling or animation skills, this study developed an authoring package that is integrated with Google 3D Warehouse, SketchUp, and a web-based 3D multi-user platform: 3D Cyber Worlds. The proposed game design authoring package was used with 53 college students for one semester, while a total of 108 students were involved in the overall study. The results indicate that the package achieved its aim of in assisting students in the game design process, including that of 3D modeling, and is feasible for future development using advance web technologies. Examples of the students’ game design projects and feedback on the use of this authoring package are also presented and discussed.

Context-based search for 3D models

Large corpora of 3D models, such as Google 3D Warehouse, are now becoming available on the web. It is possible to search these databases using a keyword search. This makes it possible for designers to easily include existing content into new scenes. In this paper, we describe a method for context-based search of 3D scenes. We first downloaded a large set of scene graphs from Google 3D Warehouse. These scene graphs were segmented into individual objects. We also extracted tags from the names of the models. Given the object shape, tags, and spatial relationship between pairs of objects, we can predict the strength of a relationship between a candidate model and an existing object in the scene. Using this function, we can perform context-based queries. The user specifies a region in the scene they are modeling using a 3D bounding box, and the system returns a list of related objects. We show that context-based queries perform better than keyword queries alone, and that without any keywords our algorithm still returns a relevant set of models.

A Combination of Augmented Reality and Google Earth’s facilities for urban planning in idea stage

This article presents a study on Augmented Reality (AR) development as a new performance approach for collaborative space of urban design work. Here, the participantse.g. architects, structure engineers, equipment vendors, etccan view an urban design process through AR scenes by Head-Mounted Display (HMD) glasses. Nowadays, the AR technology has been supported as a great graphical computing technology which promises to offer several advantages of applying for the digital architecture and construction fields. The AR effects enable users to examine 3D project models integrated into real environment in an intuitive way and real-time. Therefore, this research focuses on an establishment a kind of smart AR discussion spacethe Augmented Reality Conference Desk (named as ARCdesk for short). As the result, the participants can examine a planning process of urban design work in 3D/4D multi-phases by intuitive ways. In particular, all participants also can examine the digital urban mock-up from free views and they also can interact with whole models (or each part) during architectural discussion. As the novelty of research, the participants were suggested to manage and create the input digital urban models basing on use a range of available Google Earth facilities which are usability for architectural design, such as the Google SketchUp, Google Building Marker and Google 3D Warehouse. This example also involves the conceptual combination of AR and 4D construction simulation within indoor condition in order to simulate the phases such urban growing up. The implementation bases on the main technical theme: the imagery visionbased AR tracking and the Tangible Augmented Reality.