Coarse-to-Fine Point Cloud Shape Complementation Based on Multi-Scale Feature Fusion

被引：0
|
作者：
Zhang D. [1 ]
Wang Y. [1 ]
Tan X. [1 ]
Wu Y. [1 ]
Chen Y. [2 ]
He F. [3 ]
机构：
[1] School of Computer Science, China University of Geosciences, Wuhan
[2] Hubei Key Laboratory of Intelligent Robot, Wuhan Institute of Technology, Wuhan
[3] School of Computer, Wuhan University, Wuhan
来源：
Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics | 2024年 / 36卷 / 04期
关键词：
coarse-to-fine; encoder-decoder; multi-scale feature fusion; point cloud completion;
D O I：
10.3724/SP.J.1089.2024.19871
中图分类号：
学科分类号：
摘要：
To implement the point cloud shape completion in a coarse-to-fine manner, an end-to-end two-stage multi-scale feature fusion network is proposed, in which each stage consists of an encoder-decoder. In the first stage, the set abstraction module extracts the global features of the incomplete point cloud, which can focus on more local neighborhood features while acquiring point features of different resolutions. A decoder built from multilayer perceptrons generates a coarse skeleton. In the second stage, the coarse skeleton and incomplete point cloud are used to learn multi-scale local features. The multi-scale local features are fused with the multi-scale global features of the first stage via an attention mechanism so that each point contains global and local geometric information. Finally, the global features and multi-scale local features are progressively upsampled, and a fine-grained complete point cloud is generated via multilayer perceptrons. The point cloud completion experiments on ShapeNet, MVP, and Completion3D datasets show that the chamfer distance is reduced by 17.1%, 3.9%, and 13.9% compared with the baseline, respectively, demonstrating the effectiveness of the proposed method. © 2024 Institute of Computing Technology. All rights reserved.
引用
收藏
页码：523 / 532
页数：9
相关论文
共 34 条
  • [21] Pan L, Chen X Y, Cai Z G, Et al., Variational relational point completion network, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8524-8533, (2021)
  • [22] Xie C L, Wang C X, Zhang B, Et al., Style-based point generator with adversarial rendering for point cloud completion, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4617-4626, (2021)
  • [23] Yu X M, Rao Y M, Wang Z Y, Et al., PoinTr: diverse point cloud completion with geometry-aware transformers, Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 12498-12507, (2021)
  • [24] Komarichev A, Zhong Z C, Hua J., A-CNN: annularly convolutional neural networks on point clouds, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7421-7430, (2019)
  • [25] Li X, Wang W H, Hu X L, Et al., Selective kernel networks, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 510-519, (2019)
  • [26] Li R H, Li X Z, Fu C W, Et al., PU-GAN: a point cloud upsampling adversarial network, Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 7203-7212, (2019)
  • [27] Vakalopoulou M, Chassagnon G, Bus N, Et al., AtlasNet: multi-atlas non-linear deep networks for medical image segmentation, Proceedings of the 21st International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 658-666, (2018)
  • [28] Achlioptas P, Diamanti O, Mitliagkas I, Et al., Learning representations and generative models for 3D point clouds, Proceedings of the 35th International Conference on Learning Representations. Proceedings of the 35th International Conference on Machine Learning, pp. 40-49, (2018)
  • [29] Wen X, Xiang P, Han Z Z, Et al., PMP-net: point cloud completion by learning multi-step point moving paths, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7443-7452, (2021)
  • [30] Xiang P, Wen X, Liu Y S, Et al., SnowflakeNet: point cloud completion by snowflake point deconvolution with skip-transformer, Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 5499-5509, (2021)
1234