EUVIMEDEUVIMED entdecken
Crossref

Masked Autoencoders for 3D Point Cloud Self-supervised Learning

Yatian Pang, Eng Hock Francis Tay, Li Yuan, Zhenghua Chen

World Scientific Annual Review of Artificial Intelligence · 2024-01 · 02

DOI: 10.1142/s2811032324400010 ↗

Kurz gefasst

Fachartikel in der Zeitschrift World Scientific Annual Review of Artificial Intelligence, online erschienen am 26.02.2024. Verfasst von Yatian Pang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 32-mal zitiert (Crossref) und nennt 42 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Self-supervised learning methods are able to learn latent features from unlabeled data samples by designing pre-text tasks, and hence have attracted a great deal of interest in terms of sample-efficient learning. As a promising scheme of self-supervised learning, masked autoencoding has significantly advanced natural language processing and computer vision, but has not been introduced to point cloud yet. In this paper, we propose a novel scheme of masked autoencoders for 3D point cloud self-supervised learning, addressing the special challenges posed by point cloud, including leakage of location information and uneven information density. Concretely, we divide the input point cloud into irregular point patches and randomly mask them at a high ratio. Then, a standard Transformer-based autoencoder, with an asymmetric design and a shifting mask tokens operation, learns high-level latent features from unmasked point patches, aiming to reconstruct the masked point patches. Extensive experiments show that our approach is efficient during pre-training and generalizes well on various downstream tasks. Apart from the proposed method, we will also introduce potential directions for 3D point cloud self-supervised learning, including improvements for masked autoencoding, developments for point cloud scene understanding, etc.

Zitieren

APA

Pang, Y., Tay, E. H. F., Yuan, L., & Chen, Z. (2024). Masked Autoencoders for 3D Point Cloud Self-supervised Learning. World Scientific Annual Review of Artificial Intelligence, 02. https://doi.org/10.1142/s2811032324400010

Vancouver

Pang Y, Tay EHF, Yuan L, Chen Z. Masked Autoencoders for 3D Point Cloud Self-supervised Learning. World Scientific Annual Review of Artificial Intelligence. 2024;02. doi:10.1142/s2811032324400010

BibTeX
@article{Pang2024,
  author = {Pang, Yatian and Tay, Eng Hock Francis and Yuan, Li and Chen, Zhenghua},
  title = {Masked Autoencoders for 3D Point Cloud Self-supervised Learning},
  journal = {World Scientific Annual Review of Artificial Intelligence},
  year = {2024},
  volume = {02},
  doi = {10.1142/s2811032324400010}
}
Kostenlos starten →