.png){kind=icon}
.png){kind=icon}
Return
TreeNet: Structure preserving multi-class 3D point cloud completion
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2023.109476.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Generating the missing data of 3D object point clouds from partial observations is a challenging task. Existing state-of-the-art learning-based 3D point cloud completion methods tend to use a limited number of categories/classes of training data and regenerate the entire point cloud based on the training datasets. As a result, output 3D point clouds generated by such methods may lose details (i.e. sharp edges and topology changes) due to the lack of multi-class training. These methods also lose the structural and spatial details of partial inputs due to the models do not separate the reconstructed partial input from missing points in the output.In this paper, we propose a novel deep learning network -TreeNet for 3D point cloud completion. TreeNet has two networks in hierarchical tree-based structures: TreeNet-multiclass focuses on multi-class train-ing with a specific class of the completion task on each sub-tree to improve the quality of point cloud output; TreeNet-binary focuses on generating points in missing areas and fully preserving the original partial input. TreeNet-multiclass and TreeNet-binary are both network decoders and can be trained inde-pendently. TreeNet decoder is the combination of TreeNet-multiclass and TreeNet-binary and is trained with an encoder from existing methods (i.e. PointNet encoder). We compare the proposed TreeNet with five state-of-the-art learning-based methods on fifty classes of the public Shapenet dataset and unknown classes, which shows that TreeNet provides a significant improvement in the overall quality and exhibits strong generalization to unknown classes that are not trained.(c) 2023 The Authors. Published by Elsevier Ltd.This is an open access article under the CC BY-NC-ND license ( http://creativecommons.org/licenses/by-nc-nd/4.0/ )
Keywords:
3D Point cloud completion
Multi -class training
Hierarchical tree
Computer vision
Artificial intelligence
Deep learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W