FreePoint: Unsupervised Point Cloud Instance Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Zhikai, Ding, Jian, Jiang, Li, Dai, Dengxin, Xia, Gui-Song
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909224221540352
author Zhang, Zhikai
Ding, Jian
Jiang, Li
Dai, Dengxin
Xia, Gui-Song
author_facet Zhang, Zhikai
Ding, Jian
Jiang, Li
Dai, Dengxin
Xia, Gui-Song
contents Instance segmentation of point clouds is a crucial task in 3D field with numerous applications that involve localizing and segmenting objects in a scene. However, achieving satisfactory results requires a large number of manual annotations, which is a time-consuming and expensive process. To alleviate dependency on annotations, we propose a novel framework, FreePoint, for underexplored unsupervised class-agnostic instance segmentation on point clouds. In detail, we represent the point features by combining coordinates, colors, and self-supervised deep features. Based on the point features, we perform a bottom-up multicut algorithm to segment point clouds into coarse instance masks as pseudo labels, which are used to train a point cloud instance segmentation model. We propose an id-as-feature strategy at this stage to alleviate the randomness of the multicut algorithm and improve the pseudo labels' quality. During training, we propose a weakly-supervised two-step training strategy and corresponding losses to overcome the inaccuracy of coarse masks. FreePoint has achieved breakthroughs in unsupervised class-agnostic instance segmentation on point clouds and outperformed previous traditional methods by over 18.2% and a competitive concurrent work UnScene3D by 5.5% in AP. Additionally, when used as a pretext task and fine-tuned on S3DIS, FreePoint performs significantly better than existing self-supervised pre-training methods with limited annotations and surpasses CSC by 6.0% in AP with 10% annotation masks.
format Preprint
id arxiv_https___arxiv_org_abs_2305_06973
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle FreePoint: Unsupervised Point Cloud Instance Segmentation
Zhang, Zhikai
Ding, Jian
Jiang, Li
Dai, Dengxin
Xia, Gui-Song
Computer Vision and Pattern Recognition
Instance segmentation of point clouds is a crucial task in 3D field with numerous applications that involve localizing and segmenting objects in a scene. However, achieving satisfactory results requires a large number of manual annotations, which is a time-consuming and expensive process. To alleviate dependency on annotations, we propose a novel framework, FreePoint, for underexplored unsupervised class-agnostic instance segmentation on point clouds. In detail, we represent the point features by combining coordinates, colors, and self-supervised deep features. Based on the point features, we perform a bottom-up multicut algorithm to segment point clouds into coarse instance masks as pseudo labels, which are used to train a point cloud instance segmentation model. We propose an id-as-feature strategy at this stage to alleviate the randomness of the multicut algorithm and improve the pseudo labels' quality. During training, we propose a weakly-supervised two-step training strategy and corresponding losses to overcome the inaccuracy of coarse masks. FreePoint has achieved breakthroughs in unsupervised class-agnostic instance segmentation on point clouds and outperformed previous traditional methods by over 18.2% and a competitive concurrent work UnScene3D by 5.5% in AP. Additionally, when used as a pretext task and fine-tuned on S3DIS, FreePoint performs significantly better than existing self-supervised pre-training methods with limited annotations and surpasses CSC by 6.0% in AP with 10% annotation masks.
title FreePoint: Unsupervised Point Cloud Instance Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2305.06973