RWSeg: Cross-graph Competing Random Walks for Weakly Supervised 3D Instance Segmentation

08/10/2022
by   Shichao Dong, et al.
0

Instance segmentation on 3D point clouds has been attracting increasing attention due to its wide applications, especially in scene understanding areas. However, most existing methods require training data to be fully annotated. Manually preparing ground-truth labels at point-level is very cumbersome and labor-intensive. To address this issue, we propose a novel weakly supervised method RWSeg that only requires labeling one object with one point. With these sparse weak labels, we introduce a unified framework with two branches to propagate semantic and instance information respectively to unknown regions, using self-attention and random walk. Furthermore, we propose a Cross-graph Competing Random Walks (CGCRW) algorithm which encourages competition among different instance graphs to resolve ambiguities in closely placed objects and improve the performance on instance assignment. RWSeg can generate qualitative instance-level pseudo labels. Experimental results on ScanNet-v2 and S3DIS datasets show that our approach achieves comparable performance with fully-supervised methods and outperforms previous weakly-supervised methods by large margins. This is the first work that bridges the gap between weak and full supervision in the area.

READ FULL TEXT

page 1

page 6

research
08/03/2023

Weakly Supervised 3D Instance Segmentation without Instance-level Annotations

3D semantic scene understanding tasks have achieved great success with t...
research
03/26/2023

One Thing One Click++: Self-Training for Weakly Supervised 3D Scene Understanding

3D scene understanding, e.g., point cloud semantic and instance segmenta...
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
08/24/2022

Weakly Supervised Airway Orifice Segmentation in Video Bronchoscopy

Video bronchoscopy is routinely conducted for biopsies of lung tissue su...
research
01/03/2021

Weakly Supervised Multi-Object Tracking and Segmentation

We introduce the problem of weakly supervised Multi-Object Tracking and ...
research
02/03/2022

Weakly Supervised Nuclei Segmentation via Instance Learning

Weakly supervised nuclei segmentation is a critical problem for patholog...
research
08/17/2021

Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision

In this paper, we present a conceptually simple, strong, and efficient f...

Please sign up or login with your details

Forgot password? Click here to reset