PointAttN: You Only Need Attention for Point Cloud Completion
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (6) · 5472-5480
DOI: 10.1609/aaai.v38i6.28356 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Jun Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 91-mal zitiert (Crossref).
Abstract (Originalsprache)
Point cloud completion referring to completing 3D shapes from partial 3D point clouds is a fundamental problem for 3D point cloud analysis tasks. Benefiting from the development of deep neural networks, researches on point cloud completion have made great progress in recent years. However, the explicit local region partition like kNNs involved in existing methods makes them sensitive to the density distribution of point clouds. Moreover, it serves limited receptive fields that prevent capturing features from long-range context information. To solve the problems, we leverage the cross-attention and self-attention mechanisms to design novel neural network for point cloud completion with implicit local region partition. Two basic units Geometric Details Perception (GDP) and Self-Feature Augment (SFA) are proposed to establish the structural relationships directly among points in a simple yet effective way via attention mechanism. Then based on GDP and SFA, we construct a new framework with popular encoder-decoder architecture for point cloud completion. The proposed framework, namely PointAttN, is simple, neat and effective, which can precisely capture the structural information of 3D shapes and predict complete point clouds with detailed geometry. Experimental results demonstrate that our PointAttN outperforms state-of-the-art methods on multiple challenging benchmarks. Code is available at: https://github.com/ohhhyeahhh/PointAttN
Zitieren
APA
Wang, J., Cui, Y., Guo, D., Li, J., Liu, Q., & Shen, C. (2024). PointAttN: You Only Need Attention for Point Cloud Completion. Proceedings of the AAAI Conference on Artificial Intelligence, 38(6), 5472-5480. https://doi.org/10.1609/aaai.v38i6.28356
Vancouver
Wang J, Cui Y, Guo D, Li J, Liu Q, Shen C. PointAttN: You Only Need Attention for Point Cloud Completion. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(6):5472-5480. doi:10.1609/aaai.v38i6.28356
BibTeX
@article{Wang2024,
author = {Wang, Jun and Cui, Ying and Guo, Dongyan and Li, Junxia and Liu, Qingshan and Shen, Chunhua},
title = {PointAttN: You Only Need Attention for Point Cloud Completion},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {6},
pages = {5472--5480},
doi = {10.1609/aaai.v38i6.28356}
}
EUVIMED