PointCG

Self-supervised Point Cloud Learning via Joint Completion and Generation

Journal Article (2025)
Author(s)

Yun Liu (Nanjing University of Aeronautics and Astronautics)

Peng Li (Nanjing University of Aeronautics and Astronautics)

Xuefeng Yan (Nanjing University of Aeronautics and Astronautics)

L. Nan (TU Delft - Urban Data Science)

Bing Wang (The Hong Kong Polytechnic University)

Honghua Chen (Nanjing University of Aeronautics and Astronautics)

Lina Gong (Nanjing University of Aeronautics and Astronautics)

Wei Zhao (Nanjing University of Aeronautics and Astronautics)

Mingqiang Wei (Nanjing University of Aeronautics and Astronautics)

Research Group
Urban Data Science
DOI related publication
https://doi.org/10.1109/TVCG.2025.3526257
More Info
expand_more
Publication Year
2025
Language
English
Research Group
Urban Data Science
Bibliographical Note
Green Open Access added to TU Delft Institutional Repository as part of the Taverne amendment. More information about this copyright law amendment can be found at https://www.openaccess.nl. Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.@en
Issue number
10
Volume number
31
Pages (from-to)
6648-6660
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

The core of self-supervised point cloud learning lies in setting up appropriate pretext tasks, to construct a pre-training framework that enables the encoder to perceive 3D objects effectively. In this article, we integrate two prevalent methods, masked point modeling (MPM) and 3D-to-2D generation, as pretext tasks within a pre-training framework. We leverage the spatial awareness and precise supervision offered by these two methods to address their respective limitations: ambiguous supervision signals and insensitivity to geometric information. Specifically, the proposed framework, abbreviated as PointCG, consists of a Hidden Point Completion (HPC) module and an Arbitrary-view Image Generation (AIG) module. We first capture visible points from arbitrary views as inputs by removing hidden points. Then, HPC extracts representations of the inputs with an encoder and completes the entire shape with a decoder, while AIG is used to generate rendered images based on the visible points’ representations. Extensive experiments demonstrate the superiority of the proposed method over the baselines in various downstream tasks. Our code will be made available upon acceptance.

Files

PointCG_Self-Supervised_Point_... (pdf)
(pdf | 9.21 Mb)
- Embargo expired in 06-07-2025
License info not available