Learning part-in-whole relation of 3D shapes for part-based 3D model retrieval
Learning part-in-whole relation of 3D shapes for part-based 3D model retrieval
复制标题
DOI：
10.1016/j.cviu.2017.11.007
复制
发表时间：
2018-01-01
影响因子：
4.5
通讯作者：
Ohbuchi, Ryutarou
中科院分区：
文献类型：
--
作者：
Furuya, Takahiko;Ohbuchi, Ryutarou
给定一个指定部分3D形状的查询，基于零件的3D模型检索（P3DMR）系统会查找与查询匹配的零件或零件的3D形状。P3DMR的一种方法是将整个模型划分或分割成子部件，并执行查询部件到目标部件的匹配。无论零件的定义是什么，例如，欧几里得空间中的矩形体积或网格流形上分割的零件，计算将非常昂贵。零件-整体匹配必须考虑到数据库中每一个三维整体形状所分割的子零件的位置、比例和方向的变化。另一种方法，为了提高部分-整体匹配的效率，试图用一对特征之间的单个比较来近似部分-整体包含测试，其中一个特征代表基于部分的查询，另一个代表整个形状。例如，通过特征袋方法将零件的局部几何特征聚合为每个整体3D形状的特征。这种方法目前还存在不准确的问题，因为聚合没有针对3D形状的部分-整体包含测试进行优化。本文提出了一种新的P3DMR算法——部分-整体关系嵌入网络（PWRE-net），该算法通过学习嵌入到公共特征空间中，有效地进行部分-整体包含测试。利用深度神经网络，从大量的部分-整体形状对中学习到部分形状及其关联的整体形状的通用嵌入。对于训练，从未标记的3D模型中自动创建包含部分-整体形状对的训练数据集。实验结果表明，该方法在检索精度和检索效率方面均优于现有算法。
Given a query that specifies partial 3D shape, a Part-based 3D Model Retrieval (P3DMR) system finds 3D shapes whose part or parts matches the query. An approach to P3DMR is to partition or segment whole models into subparts and performs query-part-to-target-parts matching. Whatever the definition of part, e.g., a rectangular volume in Euclidean space or a part segmented on a mesh manifold, the computation will be very costly. The part-whole matching must account for, for each 3D whole shape in a database, varying position, scale and orientation of the segmented sub parts. Another approach, in an attempt to make part-whole matching efficient, tries to approximate part-whole inclusion test with a single comparison between a pair of features, one representing the part-based query and the other representing the whole shape. Aggregation of local geometrical features of parts into a feature per whole 3D shape, e.g., via Bag-of-Features approach, is an example. This approach so far suffered from inaccuracy as the aggregation is not optimized for part-whole inclusion test of 3D shapes. This paper proposes a novel P3DMR algorithm called Part-Whole Relation Embedding network (PWRE-net) that effectively and efficiently performs part-whole inclusion test via learned embedding into a common feature space. Using deep neural network, the PWRE-net learns, from a large number of part-whole shape pairs, a common embedding of partial shapes and their associated whole shapes. For the training, training datasets containing part-whole shape pairs are created automatically from unlabeled 3D models. Experimental evaluation shows that PWRE-net outperforms existing algorithms both in terms of retrieval accuracy and efficiency.