论文标题
周期中的映射：sindhorn正规化无监督的学习点云形状
Mapping in a cycle: Sinkhorn regularized unsupervised learning for point cloud shapes
论文作者
论文摘要
我们提出了一个无监督的学习框架，其借口任务是根据循环一致性公式从同一类别中找到点云形状之间的密集对应关系。为了从点云数据中学习判别性特征，我们将基于sndhorn归一化的正则化项合并到制剂中，以增强学到的点上刻度映射，以尽可能尽可能。此外，引入了源形状的随机刚性变换，以形成三联循环，以提高模型对扰动的鲁棒性。全面的实验表明，通过我们的框架学习的点数特征会使各种点云分析任务，例如部分形状注册和关键点传输。我们还表明，可以通过有监督的方法来利用博学的点功能，以通过完整的培训数据集或仅有的一小部分来改善零件分割性能。
We propose an unsupervised learning framework with the pretext task of finding dense correspondences between point cloud shapes from the same category based on the cycle-consistency formulation. In order to learn discriminative pointwise features from point cloud data, we incorporate in the formulation a regularization term based on Sinkhorn normalization to enhance the learned pointwise mappings to be as bijective as possible. Besides, a random rigid transform of the source shape is introduced to form a triplet cycle to improve the model's robustness against perturbations. Comprehensive experiments demonstrate that the learned pointwise features through our framework benefits various point cloud analysis tasks, e.g. partial shape registration and keypoint transfer. We also show that the learned pointwise features can be leveraged by supervised methods to improve the part segmentation performance with either the full training dataset or just a small portion of it.
