FreePoint: Unsupervised Point Cloud Instance Segmentation

05/11/2023
by   Zhikai Zhang, et al.
0

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 method, called FreePoint, for underexplored unsupervised class-agnostic instance segmentation on point clouds. In detail, we represent the point features by combining coordinates, colors, normals, and self-supervised deep features. Based on the point features, we perform a multicut algorithm to segment point clouds into coarse instance masks as pseudo labels, which are used to train a point cloud instance segmentation model. To alleviate the inaccuracy of coarse masks during training, we propose a weakly-supervised training strategy and corresponding loss. Our work can also serve as an unsupervised pre-training pretext for supervised semantic instance segmentation with limited annotations. For class-agnostic instance segmentation on point clouds, FreePoint largely fills the gap with its fully-supervised counterpart based on the state-of-the-art instance segmentation model Mask3D and even surpasses some previous fully-supervised methods. When serving as a pretext task and fine-tuning on S3DIS, FreePoint outperforms training from scratch by 5.8 mask annotations.

READ FULL TEXT

page 4

page 6

page 8

page 13

research
02/24/2022

FreeSOLO: Learning to Segment Objects without Annotations

Instance segmentation is a fundamental vision task that aims to recogniz...
research
10/11/2022

Learning Inter-Superpoint Affinity for Weakly Supervised 3D Instance Segmentation

Due to the few annotated labels of 3D point clouds, how to learn discrim...
research
10/10/2022

4D Unsupervised Object Discovery

Object discovery is a core task in computer vision. While fast progresse...
research
12/16/2020

Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts

The rapid progress in 3D scene understanding has come with growing deman...
research
12/10/2019

Learning to Optimally Segment Point Clouds

We focus on the problem of class-agnostic instance segmentation of LiDAR...
research
02/18/2019

PointIT: A Fast Tracking Framework Based on 3D Instance Segmentation

Recently most popular tracking frameworks focus on 2D image sequences. T...
research
06/24/2020

NINEPINS: Nuclei Instance Segmentation with Point Annotations

Deep learning-based methods are gaining traction in digital pathology, w...

Please sign up or login with your details

Forgot password? Click here to reset