Point Cloud Instance Segmentation using Probabilistic Embeddings
This work addresses instance segmentation in 3D point clouds for applications like robotics and autonomous driving, representing an incremental improvement over existing methods.
The paper tackles point cloud instance segmentation by introducing a framework with probabilistic embeddings and a novel loss function, achieving a 3.1% increase in average per-category mAP on the PartNet dataset.
In this paper we propose a new framework for point cloud instance segmentation. Our framework has two steps: an embedding step and a clustering step. In the embedding step, our main contribution is to propose a probabilistic embedding space for point cloud embedding. Specifically, each point is represented as a tri-variate normal distribution. In the clustering step, we propose a novel loss function, which benefits both the semantic segmentation and the clustering. Our experimental results show important improvements to the SOTA, i.e., 3.1% increased average per-category mAP on the PartNet dataset.