HPC: hierarchical point cloud completion method based on multi-scale feature points and cross attention

Xiang Huang; Zhaoyi Guo; Gu Xu; Yue Meng

doi:10.1117/12.3009122

16 October 2023 HPC: hierarchical point cloud completion method based on multi-scale feature points and cross attention

Xiang Huang, Zhaoyi Guo, Gu Xu, Yue Meng

Proceedings Volume 12803, Fifth International Conference on Artificial Intelligence and Computer Science (AICS 2023); 128032G (2023) https://doi.org/10.1117/12.3009122
Event: 2023 5th International Conference on Artificial Intelligence and Computer Science (AICS 2023), 2023, Wuhan, China

Abstract

3D Point cloud, which is considered as the simplest and most efficient shape representation for 3D objects, has been widely used in various real-world applications such as virtual reality, autonomous driving and digital twin. Point cloud completion aims to predict the complete shape structure and recover faithful details given partial observation of an incomplete input. Unlike previous completion methods based on linear architectures, this paper presents a novel hierarchical architecture for point cloud completion which divides the completion process into several levels in a coarse-to-fine manner and significantly improves the network capacity for recovering local details. First, we exploit feature connections between encoded partial inputs and decoded recovery results at the same resolution by extracting multi-scale feature points, which can provide rich information for the following generation process. Second, in order to exploit the local geometric information and interpolate the extracted features points, we introduce cross-attention based generators into the decoding phase. The cross-attention based generator preserves produced structures from previous levels and incorporate the extracted feature points into each step of a progressive generation. Extensive experiments show that our method outperforms state-of-the-art completion approaches on popular PCN and ShapeNet55 datasets.

Citation Download Citation

Xiang Huang, Zhaoyi Guo, Gu Xu, and Yue Meng "HPC: hierarchical point cloud completion method based on multi-scale feature points and cross attention", Proc. SPIE 12803, Fifth International Conference on Artificial Intelligence and Computer Science (AICS 2023), 128032G (16 October 2023); https://doi.org/10.1117/12.3009122

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
10 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Point clouds

Feature extraction

Transformers

Surface plasmons

Semantics

Ablation

Deconvolution

Show All Keywords

Keywords/Phrases

Search In:

Publication Years