Less-parametric point cloud upsampling network

Abstract

In the field of aircraft design and maintenance, with the innovation of cabin cable three-dimensional (3D) scanning and sensor technology, high-precision cabin point cloud data has become the key to improving the accuracy of cabin navigation and building a realistic virtual reality environment. In the face of largescale point cloud data, how to efficiently and uniformly construct a realistic virtual reality environment has become a challenge. In this paper, we propose a new low-parametric point cloud upsampling network (LPNet), which is based on the no-learn model to learn the complementary geometric knowledge between point clouds based on some simple data transformations, to efficiently retain the geometric properties of point clouds, and then input the results into the up-sampling module, and simply insert a few layers of multilayer perceptron (MLP) to efficiently generate high-resolution point clouds. It is able to efficiently generate high-resolution point clouds, showing great flexibility and realizing the efficient use of computational resources.

Keywords

A

References

[1] Fang Y, Zhang J L, Wen B. Research on 3D point cloud classification and segmentation based on spatial perception and feature enhancement. Journal of optoelectronics·laser, 2024, 35(07): 753-760[J]

[2] Li Y, Shen T, Zeng K. 3D target detection based on attention fusion of millimeter-wave radar point cloud and visual information disparity features. Journal of optoelectronics·laser, 2023, 34(1): 26-33[J]

[3] Li X Q, Li P H, Fang Z Det al.. Research on EEG emotion recognition based on CNN+BiLSTM+self-attention model. Optoelectronics letters, 2023, 19(8): 506-512 J]

[4] Yu L Q, Li X Z, Fu C Wet al.. PU-Net: point cloud upsampling network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 18–23, 2018, Salt Lake Sity, UT, USA, 2018, New York, IEEE[C]

[5] Yu L Q, Li X Z, Fu C Wet al.. EC-Net: an edge-aware point set consolidation network. Proceedings of the European Conference on Computer Vision, September 8–14, 2018, Munich, Germany, 2018, Heidelberg, Springer-Verlag398414[C]

[6] Ding D, Qiu C, Liu Fet al.. Point cloud upsampling via perturbation learning. IEEE transactions on circuits and systems for video technology, 2021, 31(12): 4661-4672 J]

[7] Qian G C, Abualshour A, Li Get al.. PU-GCN: point cloud upsampling using graph convolutional networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 20–25, 2021, Virtual, 2021, New York, IEEE[C]

[8] Akhtar A, Li Z, Van Der Auwera Get al.. PU-Dense: sparse tensor-based point cloud geometry upsampling. IEEE transactions on image processing, 2022, 31: 4133-4148 J]

[9] LI Q, DAI T, XIA S T. A comparative study of feature expansion unit for 3D point cloud upsampling[EB/OL]. (2022-05-19) [2024-12-23]. https://arxiv.org/abs/2205.09594.

[10] Li Z, Wang W, Lei Net al.. Weakly supervised point cloud upsampling via optimal transport. IEEE International Conference on Acoustics, Speech and Signal Processing, April 24–28, 2022, Singapore, 2022, New York, IEEE25642568[C]

[11] Chen H, Luo S, Gao Xet al.. Unsupervised learning of geometric sampling invariant representations for 3D point clouds. Proceedings of the IEEE/CVF International Conference on Computer Vision, October 10–17, 2021, Montreal, Canada, 2021, New York, IEEE893903[C]

[12] Deng L, Han B, Ren S. UPU-DGTNet: dynamic graph transformer network for unsupervised point cloud upsampling. IEEE 8th International Conference on Computer and Communications, December 9–12, 2022, Chengdu, China, 2022, New York, IEEE13951399[C]

[13] Han B, Deng L, Zheng Yet al.. UPU-SNet: Siamese network for unsupervised point cloud upsampling based on spatial-aware transformers. Computers & graphics, 2023, 115: 484-499 J]

[14] Gurram P, Hu S, Chan A. Uniform grid upsampling of 3D lidar point cloud data. Three-Dimensional Image Processing (3DIP) and Applications, February 6–7, 2013, Burlingame, California, USA, 2013, Washington, SPIE7383[C]

[15] WU H, ZHANG J, HUANG K. Point cloud super resolution with adversarial residual graph networks[EB/OL]. (2019-08-06) [2024-12-23]. https://arxiv.org/abs/1908.02111.

[16] Parker S G, Bigler J, Dietrich Aet al.. Optix: a general purpose ray tracing engine. ACM transactions on graphics (tog), 2010, 29(4): 1-13 J]

[17] Öztireli A C, Guennebaud G, Gross M. Feature preserving point set surfaces based on non-linear kernel regression. Computer graphics forum: Journal of the European Association for Computer Graphics, 2009, 28(2): 493-501 J]

[18] Borges T M, Garcia D C, De Queiroz R L. Fractional super-resolution of voxelized point clouds. IEEE transactions on image processing, 2022, 31: 1380-1390 J]

[19] Li R, Li X, Fu C Wet al.. PU-GAN: a point cloud upsampling adversarial network. Proceedings of the IEEE/CVF International Conference on Computer Vision, October 27–November 2, 2019, Seoul, South Korea, 2019, New York, IEEE72037212[C]

[20] Li X, Own C M, Wu Ket al.. CM-Net: a point cloud upsampling network based on adversarial neural network. 2021 International Joint Conference on Neural Networks, July 18–22, 2021, Shenzhen, China, 2021, New York, IEEE18[C]

[21] Liu H, Yuan H, Hamzaoui Ret al.. PU-refiner: a geometry refiner with adversarial learning for point cloud upsampling. IEEE International Conference on Acoustics, Speech and Signal Processing, April 24–28, 2022, Singapore, 2022, New York, IEEE22702274[C]

[22] Liu H, Yuan H, Hou Jet al.. PUFA-GAN: a frequency-aware generative adversarial network for 3D point cloud upsampling. IEEE transactions on image processing, 2022, 31: 7389-7402 J]

[23] Li R, Li X, Heng P Aet al.. Point cloud upsampling via disentangled refinement. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 20–25, 2021, Virtual, 2021, New York, IEEE344353[C]

[24] Han B, Zhang X, Ren S. PU-GACNet: graph attention convolution network for point cloud upsampling. Image and vision computing, 2022, 118: 104371 J]

RIGHTS & PERMISSIONS

Tianjin University of Technology