Point Cloud Instance Segmentation using Probabilistic Embeddings

Biao Zhang, Peter Wonka

2019-11-30CVPR 2021 13D Instance Segmentation Segmentation Semantic Segmentation Clustering Instance Segmentation

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.

Results

Task	Dataset	Metric	Value	Model
Instance Segmentation	PartNet	mAP50	57.5	PE
Instance Segmentation	PartNet	mAP50	57.5	Probabilistic Embeddings
3D Instance Segmentation	PartNet	mAP50	57.5	Probabilistic Embeddings

Related Papers

SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction2025-07-21 Tri-Learn Graph Fusion Network for Attributed Graph Clustering2025-07-18 Deep Learning-Based Fetal Lung Segmentation from Diffusion-weighted MRI Images and Lung Maturity Evaluation for Fetal Growth Restriction2025-07-17 DiffOSeg: Omni Medical Image Segmentation via Multi-Expert Collaboration Diffusion Model2025-07-17 From Variability To Accuracy: Conditional Bernoulli Diffusion Models with Consensus-Driven Correction for Thin Structure Segmentation2025-07-17 Unleashing Vision Foundation Models for Coronary Artery Segmentation: Parallel ViT-CNN Encoding and Variational Fusion2025-07-17 SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance Segmentation2025-07-17 Unified Medical Image Segmentation with State Space Modeling Snake2025-07-17