论文标题
神经形状编译器：用于在文本，点云和程序之间转换的统一框架
Neural Shape Compiler: A Unified Framework for Transforming between Text, Point Cloud, and Program
论文作者
论文摘要
3D形状具有从低水平几何到基于部分层次结构到语言的互补抽象，这些抽象传达了不同级别的信息。本文提出了一个统一的框架，以在成对的形状抽象之间翻译：$ \ textit {text} $ $ \ longleftrightArrow $ $ $ \ textit {point cloud} $ \ longleftrightArrow $ $ $ \ textit {program {program} $。我们建议$ \ textbf {神经形状编译器} $，以将抽象转换建模为条件生成过程。它通过提议的$ \ textit {shapecode transformer} $将三种抽象类型的3D形状转换为统一的离散形状代码，将每个形状代码转换为其他抽象类型的代码，并将它们解码以输出目标形状抽象。点云代码是通过提出的$ \ textit {point} $ vqvae以类别的方式获得的。在Text2Shape，ShapeGlot，ABO，类型和程序合成数据集上，神经形状编译器在$ \ textit {text} $ \ longrightArrow $ $ $ $ $ $ \ textit {point clive} $，$ \ textit {point count cloud cloud} $ $ \ textiT $ $ $ \ textit} $ \ longrightArrow $ $ \ textit {program} $和点云完成任务。此外，神经形状编译器受益于所有异质数据和任务的共同培训。
3D shapes have complementary abstractions from low-level geometry to part-based hierarchies to languages, which convey different levels of information. This paper presents a unified framework to translate between pairs of shape abstractions: $\textit{Text}$ $\Longleftrightarrow$ $\textit{Point Cloud}$ $\Longleftrightarrow$ $\textit{Program}$. We propose $\textbf{Neural Shape Compiler}$ to model the abstraction transformation as a conditional generation process. It converts 3D shapes of three abstract types into unified discrete shape code, transforms each shape code into code of other abstract types through the proposed $\textit{ShapeCode Transformer}$, and decodes them to output the target shape abstraction. Point Cloud code is obtained in a class-agnostic way by the proposed $\textit{Point}$VQVAE. On Text2Shape, ShapeGlot, ABO, Genre, and Program Synthetic datasets, Neural Shape Compiler shows strengths in $\textit{Text}$ $\Longrightarrow$ $\textit{Point Cloud}$, $\textit{Point Cloud}$ $\Longrightarrow$ $\textit{Text}$, $\textit{Point Cloud}$ $\Longrightarrow$ $\textit{Program}$, and Point Cloud Completion tasks. Additionally, Neural Shape Compiler benefits from jointly training on all heterogeneous data and tasks.
