Associatively Segmenting Instances and Semantics in Point Clouds

Xinlong Wang, Shu Liu, Xiaoyong Shen, Chunhua Shen, Jiaya Jia
2/26/2019
cs.CV

Official code: WXinlong/ASIS (262 stars, MIT, last commit 2019-04-27).

Abstract

A 3D point cloud describes the real scene precisely and intuitively.To date how to segment diversified elements in such an informative 3D scene is rarely discussed. In this paper, we first introduce a simple and flexible framework to segment instances and semantics in point clouds simultaneously. Then, we propose two approaches which make the two tasks take advantage of each other, leading to a win-win situation. Specifically, we make instance segmentation benefit from semantic segmentation through learning semantic-aware point-level instance embedding. Meanwhile, semantic features of the points belonging to the same instance are fused together to make more accurate per-point semantic predictions. Our method largely outperforms the state-of-the-art method in 3D instance segmentation along with a significant improvement in 3D semantic segmentation. Code has been made available at: https://github.com/WXinlong/ASIS.

View on arXivView PDF

Code Implementations(1)

WXinlong/ASISOfficial100%
MIT

Associatively Segmenting Instances and Semantics in Point Clouds, CVPR 2019

26260C++, CudaFeb 26, 20197 years agoMIT
deep-learninginstance-segmentationpoint-cloudsemantic-segmentation

Similar Papers

JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds

92% match1 repo1072019

Towards accurate instance segmentation in large-scale LiDAR point clouds

89% match1 repo1102023

JSMNet Improving Indoor Point Cloud Semantic and Instance Segmentation through Self-Attention and Multiscale

86% match2023

Small but Mighty: Enhancing 3D Point Clouds Semantic Segmentation with U-Next Framework

86% match1 repo232023

Point-Plane Projections for Accurate LiDAR Semantic Segmentation in Small Data Scenarios

85% match1 repo62025

DPGLA: Bridging the Gap between Synthetic and Real Data for Unsupervised Domain Adaptation in 3D LiDAR Semantic Segmentation

85% match2025

Cite this paper

@article{wang2019associatively,
  title  = {Associatively Segmenting Instances and Semantics in Point Clouds},
  author = {Xinlong Wang and Shu Liu and Xiaoyong Shen and Chunhua Shen and Jiaya Jia},
  year   = {2019},
  eprint = {1902.09852},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1902.09852}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1902.09852.svg)](https://codeofpaper.com/paper/1902.09852)

Discussion