Correspondences between 3D keypoints generated by matching local descriptors are a key step in 3D computer vision and graphic applications. Learned descriptors are rapidly evolving and outperforming the classical handcrafted approaches in the field. Yet, to learn effective representations they require supervision through labeled data, which are cumbersome and time-consuming to obtain. Unsupervised alternatives exist, but they lag in performance. Moreover, invariance to viewpoint changes is attained either by relying on data augmentation, which is prone to degrading upon generalization on unseen datasets, or by learning from handcrafted representations of the input which are already rotation invariant but whose effectiveness at training time may significantly affect the learned descriptor. We show how learning an equivariant 3D local descriptor instead of an invariant one can overcome both issues. LEAD (Local EquivAriant Descriptor) combines Spherical CNNs to learn an equivariant representation together with plane-folding decoders to learn without supervision. Through extensive experiments on standard surface registration datasets, we show how our proposal outperforms existing unsupervised methods by a large margin and achieves competitive results against the supervised approaches, especially in the practically very relevant scenario of transfer learning.

中文翻译：

---

点云局部等变描述符的无监督学习


通过匹配局部描述符生成的 3D 关键点之间的对应关系是 3D 计算机视觉和图形应用中的关键步骤。学习描述符正在迅速发展，并且优于该领域的经典手工方法。然而，为了学习有效的表示，他们需要通过标记数据进行监督，而获取这些数据既麻烦又耗时。存在无监督的替代方案，但它们在性能上落后。此外，视点变化的不变性可以通过依赖数据增强来实现，数据增强在对未见过的数据集进行泛化时很容易退化，或者通过从输入的手工表示中学习来实现，这些输入已经是旋转不变的，但其在训练时的有效性可能会显着影响学习到的描述符。我们展示了如何学习等变的 3D 局部描述符而不是不变的描述符可以克服这两个问题。 LEAD（局部等变描述符）将球形 CNN 与平面折叠解码器相结合来学习等变表示，以在无监督的情况下学习。通过对标准表面配准数据集的大量实验，我们展示了我们的建议如何大幅优于现有的无监督方法，并与监督方法相比取得了有竞争力的结果，特别是在实际非常相关的迁移学习场景中。