RIM-Net：用于分层形状结构无监督学习的递归隐域
RIM-Net: Recursive Implicit Fields for Unsupervised Learning of Hierarchical Shape Structures
摘要：
我们介绍RIM-Net，一个神经网络，学习递归隐域的无监督推理的层次形状结构。我们的网络递归地将输入的3D形状分解为两个部分，从而产生二叉树层次结构。树的每一级对应于形状部件的组装，表示为隐式函数，以重建输入形状。在树的每个节点处，同时特征解码和形状分解由它们各自的特征和部分解码器执行，并且权重在相同的层次级别上共享。作为隐式场解码器，部分解码器被设计为经由双向分支重构来分解子形状，其中每个分支预测定义高斯的一组参数以用作用于形状重构的局部点分布。由于每个层次都考虑了重建损失，每个节点都有分解损失，我们的网络训练不需要任何地面实况分割，更不用说层次了。通过广泛的实验和与最先进替代方案的比较，我们证明了RIM-Net分层结构推理的质量、一致性和可解释性。
英文摘要：
We introduce RIM-Net, a neural network which learns recursive implicit fields for unsupervised inference of hierarchical shape structures. Our network recursively decomposes an input 3D shape into two parts, resulting in a binary tree hierarchy. Each level of the tree corresponds to an assembly of shape parts, represented as implicit functions, to reconstruct the input shape. At each node of the tree, simultaneous feature decoding and shape decomposition are carried out by their respective feature and part decoders, with weight sharing across the same hierarchy level. As an implicit field decoder, the part decoder is designed to decompose a sub-shape, via a two-way branched reconstruction, where each branch predicts a set of parameters defining a Gaussian to serve as a local point distribution for shape reconstruction. With reconstruction losses accounted for at each hierarchy level and a decomposition loss at each node, our network training does not require any ground-truth segmentations, let alone hierarchies. Through extensive experiments and comparisons to state-of-the-art alternatives, we demonstrate the quality, consistency, and interpretability of hierarchical structural inference by RIM-Net.
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。
