Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation

by   Zhonghua Wu, et al.

Weakly supervised point cloud segmentation, i.e. semantically segmenting a point cloud with only a few labeled points in the whole 3D scene, is highly desirable due to the heavy burden of collecting abundant dense annotations for the model training. However, existing methods remain challenging to accurately segment 3D point clouds since limited annotated data may lead to insufficient guidance for label propagation to unlabeled data. Considering the smoothness-based methods have achieved promising progress, in this paper, we advocate applying the consistency constraint under various perturbations to effectively regularize unlabeled 3D points. Specifically, we propose a novel DAT (Dual Adaptive Transformations) model for weakly supervised point cloud segmentation, where the dual adaptive transformations are performed via an adversarial strategy at both point-level and region-level, aiming at enforcing the local and structural smoothness constraints on 3D point clouds. We evaluate our proposed DAT model with two popular backbones on the large-scale S3DIS and ScanNet-V2 datasets. Extensive experiments demonstrate that our model can effectively leverage the unlabeled 3D points and achieve significant performance gains on both datasets, setting new state-of-the-art performance for weakly supervised point cloud segmentation.


page 14

page 22


Dense Supervision Propagation for Weakly Supervised Semantic Segmentation on 3D Point Clouds

Semantic segmentation on 3D point clouds is an important task for 3D sce...

Reliability-Adaptive Consistency Regularization for Weakly-Supervised Point Cloud Segmentation

Weakly-supervised point cloud segmentation with extremely limited labels...

PointMatch: A Consistency Training Framework for Weakly SupervisedSemantic Segmentation of 3D Point Clouds

Semantic segmentation of point cloud usually relies on dense annotation ...

CPCM: Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic Segmentation

We study the task of weakly-supervised point cloud semantic segmentation...

Cross-modal Learning for Image-Guided Point Cloud Shape Completion

In this paper we explore the recent topic of point cloud completion, gui...

Weakly Supervised 3D Point Cloud Segmentation via Multi-Prototype Learning

Addressing the annotation challenge in 3D Point Cloud segmentation has i...

A Survey of Label-Efficient Deep Learning for 3D Point Clouds

In the past decade, deep neural networks have achieved significant progr...

Please sign up or login with your details

Forgot password? Click here to reset