ExteriorTag: Automatic Semantic Annotation of BIM Building Exterior Via Voxel Index Analysis.

The growing demand for building information modeling (BIM) data and ubiquitous applications make it increasingly necessary to establish a reliable way to share the models on lightweight devices. Building scenes have strong occlusion features and the building exterior plays an important role in digital devices with limited computational resources. This allows the possibility to reduce the resource consumption while roaming in outdoor scenes by culling away the interior building data. This article addresses the task of automatic annotation of BIM building exterior via voxel index analysis. We showcase the research of using industry foundation classes (IFC) and other mainstream formats as our input data and proposed an automatic algorithm for annotating the building exterior. Afterward, a practical and accurate voxel index analysis procedure is designed for frequently flawed models. The annotation can be added directly into the original data file under the same IFC standard, avoiding the complex procedure and information loss in semantics mapping between different standards. The final examinations show the robustness of our algorithm and the capability of handling large BIM building models.

Sketch Augmentation-Driven Shape Retrieval Learning Framework Based on Convolutional Neural Networks.

In this article, we present a deep learning approach to sketch-based shape retrieval that incorporates a few novel techniques to improve the quality of the retrieval results. First, to address the problem of scarcity of training sketch data, we present a sketch augmentation method that more closely mimics human sketches compared to simple image transformation. Our method generates more sketches from the existing training data by (i) removing a stroke, (ii) adjusting a stroke, and (iii) rotating the sketch. As such, we generate a large number of sketch samples for training our neural network. Second, we obtain the 2D renderings of each 3D model in the shape database by determining the view positions that best depict the 3D shape: i.e., avoiding self-occlusion, showing the most salient features, and following how a human would normally sketch the model. We use a convolutional neural network (CNN) to learn the best viewing positions of each 3D model and generates their 2D images for the next step. Third, our method uses a cross-domain learning strategy based on two Siamese CNNs that pair up sketches and the 2D shape images. A joint Bayesian measure is used to measure the output similarity from these CNNs to maximize inter-class similarity and minimize intra-class similarity. Extensive experiments show that our proposed approach comprehensively outperforms many existing state-of-the-art methods.

Statistical analysis and modeling of the geometry and topology of plant roots.

The root is an important organ of a plant since it is responsible for water and nutrient uptake. Analyzing and modeling variabilities in the geometry and topology of roots can help in assessing the plant's health, understanding its growth patterns, and modeling relations between plant species and between plants and their environment. In this article, we develop a framework for the statistical analysis and modeling of the geometry and topology of plant roots. We represent root structures as points in a tree-shape space equipped with a metric that quantifies geometric and topological differences between pairs of roots. We then use these building blocks to compute geodesics, i.e., optimal deformations under the metric between root structures, and to perform statistical analysis on root populations. We demonstrate the utility of the proposed framework through an application to a dataset of wheat roots grown in different environmental conditions. We also show that the framework can be used in various applications including classification and regression.