Abstract We introduce the SE (3)-Transformer, a variant of the self-attention module for 3D
point-clouds, which is equivariant under continuous 3D roto-translations. Equivariance is …

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 …

Multi-object tracking is a fundamental vision problem that has been studied for a long time.
As deep learning brings excellent performances to object detection algorithms, Tracking by …

Abstract Human-Object Interaction (HOI) detection lies at the core of action understanding.
Besides 2D information such as human/object appearance and locations, 3D pose is also …

LiDAR-based place recognition (LPR) is one of the basic capabilities of robots, which can
retrieve scenes from maps and identify previously visited locations based on 3D point …

Point cloud filtering is a fundamental problem in geometry modeling and processing.
Despite of significant advancement in recent years, the existing methods still suffer from two …

Recently, many deep neural networks were designed to process 3D point clouds, but a
common drawback is that rotation invariance is not ensured, leading to poor generalization …

With the growing availability of extensive 3D datasets and the rapid progress in
computational power, deep learning (DL) has emerged as a highly promising approach for …

We present a novel rotation invariant architecture operating directly on point cloud data. We
demonstrate how rotation invariance can be injected into a recently proposed point-based …

We present a 3D capsule module for processing point clouds that is equivariant to 3D
rotations and translations, as well as invariant to permutations of the input points. The …