LSD-StructureNet: Modeling Levels of Structural Detail in 3D Part Hierarchies
LSD-StructureNet: Modeling Levels of Structural Detail in 3D Part Hierarchies
复制标题
DOI：
10.1109/iccv48922.2021.00578
复制
发表时间：
2021-08
期刊：
影响因子：
--
通讯作者：
Dominic Roberts;Aram Danielyan;Hang Chu;M. G. Fard;David A. Forsyth
中科院分区：
文献类型：
--
作者：
Dominic Roberts;Aram Danielyan;Hang Chu;M. G. Fard;David A. Forsyth
由零件层次结构表示的3D形状的生成模型可以生成逼真和多样化的输出集合。然而，现有的模型受到整体建模形状的关键实用限制，因此不能执行条件采样，即它们不能在不修改形状的其余部分的情况下对所生成的形状的个别部分生成变体。这对3D CAD设计等涉及在多个细节级别调整创建的形状的应用程序是有限制的。为了解决这个问题，我们引入了LSD结构网，这是对结构网体系结构的一种增强，它允许重新生成位于其输出层次结构中任意位置的部件。我们通过为每个层次深度学习单独的概率条件解码器来实现这一点。我们在Partnet数据集上评估了LSD结构网，Partnet数据集是由零件层次结构表示的3D形状的最大数据集。结果表明，与已有方法相反，LSD-结构网可以在不影响推理速度和输出的真实性和多样性的情况下进行条件采样。
Generative models for 3D shapes represented by hierarchies of parts can generate realistic and diverse sets of outputs. However, existing models suffer from the key practical limitation of modelling shapes holistically and thus cannot perform conditional sampling, i.e. they are not able to generate variants on individual parts of generated shapes without modifying the rest of the shape. This is limiting for applications such as 3D CAD design that involve adjusting created shapes at multiple levels of detail. To address this, we introduce LSD-StructureNet, an augmentation to the StructureNet architecture that enables re-generation of parts situated at arbitrary positions in the hierarchies of its outputs. We achieve this by learning individual, probabilistic conditional decoders for each hierarchy depth. We evaluate LSD-StructureNet on the PartNet dataset, the largest dataset of 3D shapes represented by hierarchies of parts. Our results show that contrarily to existing methods, LSD-StructureNet can perform conditional sampling without impacting inference speed or the realism and diversity of its outputs.