Deformation-Aware 3D Model Embedding and Retrieval
Deformation-Aware 3D Model Embedding and Retrieval
复制标题
DOI：
10.1007/978-3-030-58571-6_24
复制
发表时间：
2020-04
期刊：
影响因子：
--
通讯作者：
Mikaela Angelina Uy;Jingwei Huang;Minhyuk Sung;Tolga Birdal;L. Guibas
中科院分区：
文献类型：
--
作者：
Mikaela Angelina Uy;Jingwei Huang;Minhyuk Sung;Tolga Birdal;L. Guibas
我们引入了一个新的问题，检索3D模型，变形到一个给定的查询形状，并提出了一种新的deepdeformation-award嵌入来解决这个检索任务。3D模型检索是用于从噪声和部分3D扫描中恢复干净和完整的3D模型的基本操作。然而，给定有限的3D形状集合，即使是最接近查询的模型也可能不令人满意。这促使我们应用3D模型变形技术来适应检索到的模型，以便更好地适应查询。然而，在大多数3D变形技术中强制执行某些限制，以保留原始模型的重要特征，这些特征阻止变形模型与查询的完美拟合。变形模型和查询之间的这种差距会导致模型之间的不对称关系，这是典型的度量学习技术无法处理的。因此，为了检索最佳拟合模型，我们提出了一种新的深度嵌入方法，该方法通过利用位置相关的自我中心距离场来学习非对称关系。我们还提出了两种嵌入网络的训练策略。我们证明，这两种方法优于其他基线在我们的实验与合成和真实的数据。我们的项目页面可以在 deformscan2cad.github.io .
We introduce a new problem ofretrieving3D models that aredeformableto a given query shape and present a novel deepdeformation-awareembedding to solve this retrieval task. 3D model retrieval is a fundamental operation for recovering a clean and complete 3D model from a noisy and partial 3D scan. However, given a finite collection of 3D shapes, even the closest model to a query may not be satisfactory. This motivates us to apply 3D model deformation techniques to adapt the retrieved model so as to better fit the query. Yet, certain restrictions are enforced in most 3D deformation techniques to preserve important features of the original model that prevent a perfect fitting of the deformed model to the query. This gap between the deformed model and the query inducesasymmetricrelationships among the models, which cannot be handled by typical metric learning techniques. Thus, to retrieve the best models for fitting, we propose a novel deep embedding approach that learns the asymmetric relationships by leveraging location-dependent egocentric distance fields. We also propose two strategies for training the embedding network. We demonstrate that both of these approaches outperform other baselines in our experiments with both synthetic and real data. Our project page can be found at deformscan2cad.github.io .