Neural Shape Parsers for Constructive Solid Geometry
Neural Shape Parsers for Constructive Solid Geometry
复制标题
构造立体几何的神经形状解析器
DOI：
10.1109/tpami.2020.3044749
复制
发表时间：
2019-12
影响因子：
23.6
通讯作者：
Gopal Sharma;Rishabh Goyal;Difan Liu;E. Kalogerakis;Subhransu Maji
中科院分区：
文献类型：
--
作者：
Gopal Sharma;Rishabh Goyal;Difan Liu;E. Kalogerakis;Subhransu Maji
构造性实体几何（CSG）是一种几何建模技术，其通过递归地对诸如球体和圆柱体之类的基元应用布尔运算来定义复杂形状。我们提出了CSGNet，一个深度网络架构，它以2D或3D形状作为输入，并输出一个CSG程序来对其进行建模。将形状解析为CSG程序是可取的，因为它会产生一个紧凑且可解释的生成模型。然而，这项任务是具有挑战性的，因为基元及其组合的空间可以是非常大的。CSGNet使用基于深度网络的卷积编码器和递归解码器，以前馈方式将形状映射到建模指令，并且比自下而上的方法快得多。我们调查了两个架构，这个任务的香草编码器（CNN）解码器（RNN）和另一种架构，增强了编码器与显式内存模块的基础上的程序执行堆栈。堆栈增强提高了生成的形状的重建质量和学习效率。我们的方法也是更有效的形状原语检测器相比，国家的最先进的对象检测器。最后，我们证明CSGNet可以通过策略梯度技术在没有程序注释的新数据集上进行训练。
Constructive solid geometry (CSG) is a geometric modeling technique that defines complex shapes by recursively applying boolean operations on primitives such as spheres and cylinders. We present CSGNet, a deep network architecture that takes as input a 2D or 3D shape and outputs a CSG program that models it. Parsing shapes into CSG programs is desirable as it yields a compact and interpretable generative model. However, the task is challenging since the space of primitives and their combinations can be prohibitively large. CSGNet uses a convolutional encoder and recurrent decoder based on deep networks to map shapes to modeling instructions in a feed-forward manner and is significantly faster than bottom-up approaches. We investigate two architectures for this task—a vanilla encoder (CNN) - decoder (RNN) and another architecture that augments the encoder with an explicit memory module based on the program execution stack. The stack augmentation improves the reconstruction quality of the generated shape and learning efficiency. Our approach is also more effective as a shape primitive detector compared to a state-of-the-art object detector. Finally, we demonstrate CSGNet can be trained on novel datasets without program annotations through policy gradient techniques.