Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation

TL;DR

This paper introduces DAT, a dual adaptive transformation approach that uses adversarial strategies to enforce smoothness constraints, significantly improving weakly supervised 3D point cloud segmentation performance.

Contribution

The paper proposes a novel DAT model applying dual adaptive transformations via adversarial strategies to enhance label propagation in weakly supervised point cloud segmentation.

Findings

Achieves state-of-the-art results on S3DIS and ScanNet-V2 datasets.

Effectively leverages unlabeled 3D points for improved segmentation.

Demonstrates significant performance gains over existing methods.

Abstract

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 (\textbf{D}ual \textbf{A}daptive \textbf{T}ransformations) 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.