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.
翻译:我们引入了 RIM- Net, 这是一种神经网络, 学习循环隐含的隐含字段, 用于不受监督的等级形状结构的推断。 我们的网络将输入的 3D 形状分解成两部分, 形成双树分层。 树的每层对应一个形状部件的集合, 以隐含功能表示, 以重建输入形状。 在树的每个节点, 同步特征解码和形状分解由它们各自的特性和部分分解器进行, 其重量在同一等级层次之间共享。 作为隐含的分解场, 部分分解器的设计通过双向分层重建将输入的子形状分层分解成两部分, 每个分支都预测了一组参数, 定义一个高山作为形状重建的局部点分布。 由于每个分层层次的重建损失和每个节点的分解损失, 我们的网络培训不需要任何地面分解, 更不用说等级分解。 通过广泛的实验和比较, 以RIM 结构显示质量、 一致性和可解释性 。