计算机科学
杠杆(统计)
人工智能
钥匙(锁)
代表(政治)
活动形状模型
形状分析(程序分析)
编码(集合论)
模式识别(心理学)
相似性(几何)
图像(数学)
静态分析
计算机安全
集合(抽象数据类型)
分割
政治
政治学
法学
程序设计语言
作者
Bo Sun,Vladimir G. Kim,Noam Aigerman,Qixing Huang,Siddhartha Chaudhuri
标识
DOI:10.1007/978-3-031-20062-5_29
摘要
This paper introduces a data-driven shape completion approach that focuses on completing geometric details of missing regions of 3D shapes. We observe that existing generative methods lack the training data and representation capacity to synthesize plausible, fine-grained details with complex geometry and topology. Our key insight is to copy and deform patches from the partial input to complete missing regions. This enables us to preserve the style of local geometric features, even if it drastically differs from the training data. Our fully automatic approach proceeds in two stages. First, we learn to retrieve candidate patches from the input shape. Second, we select and deform some of the retrieved candidates to seamlessly blend them into the complete shape. This method combines the advantages of the two most common completion methods: similarity-based single-instance completion, and completion by learning a shape space. We leverage repeating patterns by retrieving patches from the partial input, and learn global structural priors by using a neural network to guide the retrieval and deformation steps. Experimental results show our approach considerably outperforms baselines across multiple datasets and shape categories. Code and data are available at https://github.com/GitBoSun/PatchRD .
科研通智能强力驱动
Strongly Powered by AbleSci AI