Dual adaptive transformations for weakly supervised point cloud segmentation

Zhonghua Wu, Yicheng Wu, Guosheng Lin, Jianfei Cai, Chen Qian

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

12 Citations (Scopus)

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 (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.

Original languageEnglish
Title of host publicationComputer Vision – ECCV 2022 - 17th European Conference Tel Aviv, Israel, October 23–27, 2022 Proceedings, Part XXXI
EditorsShai Avidan, Gabriel Brostow, Moustapha Cissé, Giovanni Maria Farinella, Tal Hassner
Place of PublicationCham Switzerland
PublisherSpringer
Pages78-96
Number of pages19
ISBN (Electronic)9783031198212
ISBN (Print)9783031198205
DOIs
Publication statusPublished - 2022
EventEuropean Conference on Computer Vision 2022 - Tel Aviv, Israel
Duration: 23 Oct 202227 Oct 2022
Conference number: 17th
https://link.springer.com/book/10.1007/978-3-031-19830-4 (Proceedings)
https://eccv2022.ecva.net (Website)

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume13691
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceEuropean Conference on Computer Vision 2022
Abbreviated titleECCV 2022
Country/TerritoryIsrael
CityTel Aviv
Period23/10/2227/10/22
Internet address

Keywords

  • Dual adaptive transformations
  • Point cloud segmentation
  • Weakly supervised segmentation

Cite this