论文标题
使用SE（3） - 等级矢量神经元的形状置孔分离
Shape-Pose Disentanglement using SE(3)-equivariant Vector Neurons
论文作者
论文摘要
我们通过解开形状和姿势引入了一种无监督的技术，以将点云编码为规范形状表示。我们的编码器是稳定且一致的，这意味着编码的形状纯粹是姿势不变的，而提取的旋转和翻译能够在语义上与同一类的不同输入形状与常见的规范姿势保持一致。具体而言，我们设计了一个基于旋转等级神经网络向量神经元网络的自动编码器，除了旋转 - 等效性外，我们扩展了其层以提供翻译 - 均衡性。由此产生的编码器会通过构造产生姿势不变的形状，使我们的方法能够专注于学习一类对象的一致规范姿势。定量和定性实验验证了我们方法的出色稳定性和一致性。
We introduce an unsupervised technique for encoding point clouds into a canonical shape representation, by disentangling shape and pose. Our encoder is stable and consistent, meaning that the shape encoding is purely pose-invariant, while the extracted rotation and translation are able to semantically align different input shapes of the same class to a common canonical pose. Specifically, we design an auto-encoder based on Vector Neuron Networks, a rotation-equivariant neural network, whose layers we extend to provide translation-equivariance in addition to rotation-equivariance only. The resulting encoder produces pose-invariant shape encoding by construction, enabling our approach to focus on learning a consistent canonical pose for a class of objects. Quantitative and qualitative experiments validate the superior stability and consistency of our approach.
