arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.13459cs.CVcs.GR
收藏

LSD-StructureNet:三维零件层次中结构细节的建模级别

LSD-StructureNet: Modeling Levels of Structural Detail in 3D Part Hierarchies

University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Autodesk AI Lab(Autodesk AI 实验室)

Dominic Roberts, Ara Danielyan, Hang Chu, Mani Golparvar-Fard, David Forsyth

摘要:

由零件层次结构表示的3D形状的生成模型可以生成逼真且多样化的输出集。然而,现有模型受到整体建模形状的关键实际限制,因此无法执行条件采样,即它们无法在不修改形状其余部分的情况下生成所生成形状的各个部分的变体。这限制了诸如3D CAD设计的应用,这些应用涉及在多个细节级别上调整所创建的形状。为了解决这个问题,我们引入了LSD-StructureNet,这是对StructureNet架构的增强,可以重新生成位于其输出层次结构中任意位置的部件。我们通过学习每个层次深度的个体概率条件解码器来实现这一点。我们在PartNet数据集上评估LSD-StructureNet,PartNet数据集是由零件层次结构表示的3D形状的最大数据集。我们的研究结果表明,与现有的方法相反,LSD-StructureNet可以执行条件采样,而不会影响推理速度或其输出的真实性和多样性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑