Point cloud learning has lately attracted increasing attention due to its wide applications in
many areas, such as computer vision, autonomous driving, and robotics. As a dominating …

Existing state-of-the-art 3D instance segmentation methods perform semantic segmentation
followed by grou**. The hard predictions are made when performing semantic …

Most existing methods realize 3D instance segmentation by extending those models used
for 3D object detection or 3D semantic segmentation. However, these non-straightforward …

In this paper, we introduce SalsaNext for the uncertainty-aware semantic segmentation of a
full 3D LiDAR point cloud in real-time. SalsaNext is the next version of SalsaNet 1 which has …

Existing 3D instance segmentation methods are predominated by the bottom-up design--
manually fine-tuned algorithm to group points into clusters followed by a refinement network …

Recently, transformer-based methods have dominated 3D instance segmentation, where
mask attention is commonly involved. Specifically, object queries are guided by the initial …

Generalizable 3D part segmentation is important but challenging in vision and robotics.
Training deep models via conventional supervised methods requires large-scale 3D …

Instance segmentation in 3D scenes is fundamental in many applications of scene
understanding. It is yet challenging due to the compound factors of data irregularity and …

Abstract 3D point cloud panoptic segmentation is the combined task to (i) assign each point
to a semantic class and (ii) separate the points in each class into object instances. Recently …

We introduce a 3D instance representation, termed instance kernels, where instances are
represented by one-dimensional vectors that encode the semantic, positional, and shape …