Journal
KNOWLEDGE-BASED SYSTEMS
Volume 255, Issue -, Pages -Publisher
ELSEVIER
DOI: 10.1016/j.knosys.2022.109770
Keywords
Deep learning; Point cloud; Completion; Feature extraction
Categories
Funding
- National Natural Science Foundation of China
- Zhejiang Provincial Natural Science Founda- tion of China
- [62032022]
- [62176244]
- [62006215]
- [LZ20F030001]
- [LQ20F030016]
Ask authors/readers for more resources
This paper presents a novel network model that adopts a coarse-to-fine point cloud completion strategy. It can adaptively aggregate the latent shape information in local features and generate high-resolution complete point clouds. The experimental results on different datasets verify the excellent performance of the model in point cloud completion task.
Point cloud data obtained by 3D scanning equipment is often incomplete. In recent years, to complete the missing point clouds has become an important task in computer visualization research. This paper adopts a coarse-to-fine completion strategy and build a novel adaptive region shape fused network (ARSF-Net), which contains three core modules, namely region shape encoding module (RSE), adaptive feature selection-aggregation module (ASA), and encoding-attention transformer module (EAT). The RSE module adaptively aggregates the latent shape information contained in local features according to the feature strength. In ASA module, we first treat point coordinates and shape features as parent nodes and design a hybrid correlation method to adaptively group parent nodes. Then, each set of parent nodes generates a child node. Finally, we splice the features and points in the parent node and child node separately to double the number. For EAT module, we learn features from the encoding stage and use a coordinate-based embedding transformer to generate uniform high-resolution point clouds. Compared with previous methods, we pay special attention to the difference among the latent shape information contained in the local point clouds, thus making the local feature extraction more interpretable. At the same time, to generate valid detail features from the original ones, we abundantly consider the correlation among the original ones, and directly combine the original features with the generated ones. Our experiments on different datasets verify the good performance of ARSF-Net in the point cloud completion task.(c) 2022 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available