The attention module is the key component in Transformers. While the global attention
mechanism offers high expressiveness, its excessive computational cost restricts its …

Capsule networks emerged as a promising alternative to convolutional neural networks for
learning object-centric representations. The idea is to explicitly model part-whole hierarchies …

Extracting robust and general 3D local features is key to downstream tasks such as point
cloud registration and reconstruction. Existing learning-based local descriptors are either …

We introduce a new general-purpose approach to deep learning on three-dimensional
surfaces based on the insight that a simple diffusion layer is highly effective for spatial …

We present RoReg, a novel point cloud registration framework that fully exploits oriented
descriptors and estimated local rotations in the whole registration pipeline. Previous …

There has been enormous progress in the last few years in designing neural networks that
respect the fundamental symmetries and coordinate freedoms of physical law. Some of …

In this paper, we propose a novel local descriptor-based framework, called You Only
Hypothesize Once (YOHO), for the registration of two unaligned point clouds. In contrast to …

Features that are equivariant to a larger group of symmetries have been shown to be more
discriminative and powerful in recent studies. However, higher-order equivariant features …

Disobeying the classical wisdom of statistical learning theory, modern deep neural networks
generalize well even though they typically contain millions of parameters. Recently, it has …

We propose a self-supervised capsule architecture for 3D point clouds. We compute capsule
decompositions of objects through permutation-equivariant attention, and self-supervise the …