TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
3D Instance Segmentation	PartNet	Probabilistic Embeddings	mAP50	57.5	# 2
Instance Segmentation	PartNet	PE	mAP50	57.5	# 1

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/point-cloud-instance-segmentation-using/instance-segmentation-on-partnet)](https://paperswithcode.com/sota/instance-segmentation-on-partnet?p=point-cloud-instance-segmentation-using)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/point-cloud-instance-segmentation-using/3d-instance-segmentation-on-partnet)](https://paperswithcode.com/sota/3d-instance-segmentation-on-partnet?p=point-cloud-instance-segmentation-using)`

Point Cloud Instance Segmentation using Probabilistic Embeddings

CVPR 2021 · Biao Zhang, Peter Wonka ·

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.