Recent advances in machine learning have led to increased interest in solving visual
computing problems using methods that employ coordinate‐based neural networks. These …

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

The construction of 3D point cloud datasets requires a great deal of human effort. Therefore,
constructing a largescale 3D point clouds dataset is difficult. In order to remedy this issue …

We consider the deep point cloud analysis tasks where the inputs of the networks are
randomly rotated. Recent progress in rotation-invariant point cloud analysis is mainly driven …

Progress in 3D object understanding has relied on manually" canonicalized" shape datasets
that contain instances with consistent position and orientation (3D pose). This has made it …

Recent progress in introducing rotation invariance (RI) to 3D deep learning methods is
mainly made by designing RI features to replace 3D coordinates as input. The key to this …

With the explosive 3D data growth, the urgency of utilizing zero-shot learning to facilitate
data labeling becomes evident. Recently, methods transferring language or language …

Soft-argmax operation is commonly adopted in detection-based methods to localize the
target position in a differentiable manner. However, training the neural network with soft …

Coordinate-based implicit neural networks, or neural fields, have emerged as useful
representations of shape and appearance in 3D computer vision. Despite advances …