Point cloud instance segmentation using probabilistic embeddings


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.

In 2021 Conference on Computer Vision and Pattern Recognition
Biao Zhang
Biao Zhang
PhD candidate

My research interests include machine learning, deep learning and 3d vision.