Point Cloud Instance Segmentation using Probabilistic Embeddings

Biao Zhang, Peter Wonka

Keywords: point clouds, instance segmentation, uncertainty estimation, probabilistic embedding

Abstract: 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.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: We propose a instance segmentation method which is able to estimate uncertainty by using probabilistic embeddings.

Reviewed Version (pdf): https://openreview.net/references/pdf?id=sjhQi7d3Q6