Point Cloud Geometry Coding Framework Based on Sampling

doi:10.12141/j.issn.1000-565X.230188

Abstract

Abstract:

With the development of science and technology, the accuracy of 3D point cloud acquisition equipment has been continuously improved, and the acquisition of massive 3D point cloud data has become a reality. However, the irregular distribution and huge number of data points of 3D point cloud bring great challenges to data storage and transmission. Therefore, 3D point cloud coding is imperative. From the perspective of data sampling, this paper transforms the 3D point cloud coding problem into a 3D point cloud sampling-reconstruction problem, and proposes a sampling-based 3D point cloud geometry coding framework. In this framework, firstly, the down-sampling method is used to sample the original 3D point cloud to the sparse 3D point cloud with a specified number of points. Then, the sparse 3D point cloud is encoded using any existing coding methods (the number of encoding points is significantly reduced, which can effectively reduce the encoding rate). Finally, by using the proposed upsampling method, the decoded sparse 3D point cloud is interpolated as a high-quality dense 3D point cloud similar to the shape of the original input point cloud. Experimental results show that, as compared with the latest G-PCC provided by MPEG, the proposed 3D point cloud geometry coding framework improves the objective quality of the reconstructed 3D point cloud by 5.49 dB on average, and presents better subjective visual effect.

Key words: point cloud, geometry coding, deep learning, sampling

CLC Number:

TN919

LIU Hao, YUAN Hui, CHEN Chen, GAO Wei. Point Cloud Geometry Coding Framework Based on Sampling[J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(6): 148-156.

Figures/Tables 10

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Table 1

Fig.6

Fig.7

Table 2

Table 3

References 34

1	ZHANG C， CAI Q，CHOU，et al ．Viewport：a distributed，immersive teleconferencing system with infrared dot pattern［J］．IEEE Multimedia，2013，20（4）：17-27．
2	SCHNABEL R， KLEIN R ．Octree-based point-cloud compression［C］∥Proceedings of the 3rd Eurographics．Berlin：Eurographics Association，2006：12-22．
3	G-PCC codec description：ISO/IEC ［S］．
4	V-PCC codec description：ISO/IEC ［S］．
5	HUANG Y， PENG J L， KUO C-C，et al ．A generic scheme for progressive point cloud coding［J］．IEEE Transactions on Visualization and Computer Graphics，2008，14（2）：440-453．
6	RENTE P D O， BRITES C， ASCENSO J ．M，et al．Graph-based static 3d point clouds geometry coding［J］．IEEE Transactions on Multimedia，2018，21（2）：284-299．
7	张旭康，牛报宁，张锦文．向量相似度可复原三维点云压缩算法［J］．计算机科学与探索，2020，14（4）：657-668．
	ZHANG Xukang， NIU Baoning， ZHANG Jinwen ．Recoverable 3d point cloud compression algorithm based on vector similarity［J］．Journal of Frontiers of Computer Science and Technology，2020，14（4）：657-668．
8	KALAIAH A， VARSHNEY A ．Statistical geometry representation for efficient transmission and rendering［J］．ACM Transactions on Graphics，2005，24（2）：348-373．
9	SONG F， SHAO Y， GAO W，et al ．Layer-wise geometry aggregation framework for lossless lidar point cloud compression［J］．IEEE Transactions on Circuits and Systems for Video Technology，2021，31（12）：4603-4616．
10	WANG J， ZHU H， LIU H，et al ．Lossy point cloud geometry compression via end-to-end learning［J］．IEEE Transactions on Circuits and Systems for Video Technology，2021，31（12）：4909-4923．
11	MATSUZAKI K， TASAKA K，Binary representation for 3d point cloud compression based on deep auto-encoder［C］∥Proceedings of IEEE Global Conference on Consumer Electronics．Osaka：IEEE，2019：489-490．
12	HUANG L， WANG S， WONG K，et al ．OctSqueeze：octree structured entropy model for lidar compression［C］∥Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition．Seattle：IEEE，2020：1310-1320．
13	SUN X， WANG S， LIU M ．A novel coding architecture for multiline lidar point clouds based on clustering and convolutional lstm network［J］．IEEE Transactions on Intelligent Transportation Systems，2022，23（3）：2190-2201．
14	NGUYEN D T， QUACH M， VALENZISE G，et al ．Lossless coding of point cloud geometry using a deep generative model［J］．IEEE Transactions on Circuits and Systems for Video Technology，2021，31（12）：4617-4629．
15	ZHAO L， MA K-K， LIN X，et al ．Real-time lidar point cloud compression using bi-directional prediction and range-adaptive floating-point coding［J］．IEEE Transactions on Broadcasting，2022，68（3）：620-635．
16	WANG J， DING D， LI Z，et al ．Sparse tensor-based multiscale representation for point cloud geometry compression［J］．IEEE Transactions on Pattern Analysis and Machine Intelligence，2023，45（7）：9055-9071．
17	WEI Z， NIU B， XIAO H，et al ．Isolated points prediction via deep neural network on point cloud lossless geometry compression［J］．IEEE Transactions on Circuits and Systems for Video Technology，2023，33（1）：407-420．
18	ELDAR Y， LINDENBAUM M ．The farthest point strategy for progressive image sampling［J］．IEEE Transactions on Image Processing，1997，6（9）：1305-1315．
19	QUEIROZ R L D， CHOU P A ．Compression of 3d point clouds using a region-adaptive hierarchical transform［J］．IEEE Transactions on Image Processing，2016，25（8）：3947-3956．
20	ALEXA M， BEHR J， COHEN-OR D，et al ．Computing and rendering point set surfaces［J］．IEEE Transactions on Visualization and Computer Graphics，2003，9（1）：3-15．
21	LIPMAN Y， COHEN-OR D， LEVIN D，et al ．Parameterization-free projection for geometry reconstruction［J］．ACM Transactions on Graphic，2007，26（3）：209-218．
22	HUANG H， WU S， GONG M，et al ．Edge-aware point set resampling［J］．ACM Transactions on Gra-phics，2013，32（1）：1-12．
23	YU L， LI X， FU C W，et al ．PU-Net：point cloud upsampling network［C］∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition．Salt Lake City：IEEE，2018：2790-2799．
24	WANG Y， WU S， HUANG H，et al ．Patch-based progressive 3d point set upsampling［C］∥Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition．Long Beach：IEEE，2019：5958-5967．
25	QIAN Y， HOU J， KWONG K，et al ．PUGeo-Net： a geometry-centric network for 3d point cloud upsampling［C］∥Proceedings of European Conference on Computer Vision．Berlin：Springer，2020：752-769．
26	LIU H， YUAN H， HAMZAOUI R，et al ．PU-Refiner：a geometry refiner with adversarial learning for point cloud upsampling［C］∥Proceedings of IEEE International Conference on Acoustics，Speech and Signal Processing．Singapore：IEEE，2022：2270-2274．
27	YANG Y， FENG C， SHEN Y，et al ．FoldingNet： point cloud auto-encoder via deep grid deformation［C］∥Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition．Salt Lake City：IEEE，2018：206-215．
28	VASWANI A， SHAZEER N， PARMAR N，et al ．Attention is all you need［C］∥Proceedings of Advances in Neural Information Processing Systems．Long Beach：NIPS，2017：5998-6008．
29	HE K， ZHANG X， REN S，et al ．Deep residual learning for image recognition［C］∥Proceedings of IEEE Conference on Computer Vision and Pattern Re-cognition．Las Vegas：IEEE，2016：770-778．
30	LI R， LI X， FU C，et al ．PU-GAN： a point cloud upsampling adversarial network［C］∥Proceedings of IEEE/CVF International Conference on Computer Vision．Seoul：IEEE，2019：7202-7211．
31	Evaluation metrics for point cloud compression：ISO/IEC m39966［S］．
32	Improvements of the bd-psnr model：VCEG-AI11 ［S］．
33	YUAN H， ZHANG D， WANG W，et al ．A sampling-based 3D point cloud compression algorithm for immersive communication［J］．Mobile Networks and Applications，2020，25（5）：1863-1872．
34	QIAN G， ABUALSHOUR A， LI G，et al ．PU-GCN：point cloud upsampling using graph convolutional networks［C］∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition．Nashville：IEEE，2021：11678-11687．

数据集	BD-PSNR/dB
数据集	文献［33］方法	文中方法
平均结果	-1.76	5.49
11509_Panda_v4	-2.08	4.54
13770_Tiger_V1	-2.37	6.66
camel	-3.86	6.02
casting	-4.98	3.06
chair	-3.65	5.66
cow	-2.01	6.15
duck	-1.62	4.21
eight	1.42	6.59
elk	-3.41	4.36
genus3	-1.08	5.19
kitten	-0.94	5.57
m32	-1.82	6.31
m60	-0.03	6.32
m329	-0.27	5.89
m333	-1.67	4.97
m355	-1.43	4.97
pig	-0.01	6.06
star	-0.39	5.48
statue_ramesses	-2.69	5.90
statue_rome	-2.28	5.91

数据集	不同上采样方法时的PSNR/dB
数据集	PU-Refiner	PU-GCN	PU-GAN	PU-Geo	MPU
平均结果	59.34	59.19	59.07	58.66	57.81
11509_Panda_v4	57.75	57.40	57.60	56.82	55.93
13770_Tiger_V1	61.60	61.53	61.03	60.89	60.15
camel	59.81	59.70	59.50	59.11	58.21
casting	57.61	57.28	57.10	56.94	56.16
chair	60.33	60.26	59.70	59.78	58.92
cow	60.23	60.17	59.90	59.78	58.71
duck	57.28	57.06	57.24	56.61	55.65
eight	60.41	60.32	60.14	59.72	58.95
elk	57.19	56.97	57.07	56.45	55.62
genus3	58.38	58.08	58.21	57.57	56.73
kitten	58.91	58.73	58.78	58.17	57.26
m32	60.77	60.79	60.38	60.13	59.35
m60	61.76	61.80	61.21	61.33	60.64
m329	59.51	59.34	59.28	58.70	57.88
m333	58.21	57.98	58.12	57.48	56.61
m355	58.40	58.16	58.34	57.74	56.80
pig	59.70	59.62	59.50	59.09	58.20
star	58.47	58.24	58.36	57.70	56.82
statue_ramesses	60.10	59.99	59.78	59.38	58.56
statue_rome	60.44	60.35	60.10	59.79	59.10

步骤	编码时间/s
步骤	G-PCC	文献［33］方法	文中方法
总时间	0.59	2.40	5.60
下采样	—	0.83	0.83
编码	0.59	0.16	0.16
上采样	—	1.41	4.61

[1]	PENG Yipu, LI Jian, HAN Yanqun, TANG Zhiyuan, LI Zichao, YU Fengxiao, CHEN Li, ZOU Kui. Alignment Analysis of Railway Steel Truss Arch Bridge Based on Point Cloud Slicing Algorithm [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(7): 97-106.
[2]	HU Xizhi, CUI Bofei, WANG Qin, et al. Visual SLAM Algorithm Based on Memory Parking Scene [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(6): 1-11.
[3]	HU Yongjian, ZHUO Sichao, LIU Beibei, WANG Yufei, LI Jicheng. Improvement of Cross-Dataset Performance of Face Forgery Detection Based on Multi-Scale Spatiotemporal Features and Tampering Probabilities [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(6): 110-119.
[4]	YANG Chunling, LIANG Ziwen. Feature-Domain Proximal High-Dimensional Gradient Descent Network for Image Compressed Sensing [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(3): 119-130.
[5]	ZHENG Juanyi, DONG Jiahao, ZHANG Qingjue, et al. Reconfigurable Intelligence Surface Channel Estimation Algorithm Based on RDN [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(3): 102-111.
[6]	ZHOU Lang, FAN Kun, QU Hua, et al. Forest Fire Recognition by Improved EfficientNet-E Model Based on ECA Attention Mechanism [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(2): 42-49.
[7]	CAI Xiaodong, ZHOU Qingsong, YE Qing. Social Recommendation Model Based on Dynamic Neighborhood Sampling [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(2): 32-41.
[8]	TIAN Sheng, SONG Lin, ZHAO Kailong. Point Cloud Classification Based on Offset Attention Mechanism and Multi-Feature Fusion [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(1): 100-109.
[9]	LI Fang, GUO Weisen, ZHANG Ping, et al.. Prediction Technique for Remaining Useful Life of Bearing Based on Spatial-Temporal Dual Cell State [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(9): 69-81.
[10]	SU Jindian, YU Shanshan, HONG Xiaobin. A Self-Supervised Pre-Training Method for Chinese Spelling Correction [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(9): 90-98.
[11]	LI Jiachun, LI Bowen, LIN Weiwei. AdfNet: An Adaptive Deep Forgery Detection Network Based on Diverse Features [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(9): 82-89.
[12]	GUO Enqiang, FU Xinsha. Dropped Object Detection Method Based on Feature Similarity Learning [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(6): 30-41.
[13]	ZHAO Jiandong, JIAO Lanxin, ZHAO Zhimin, et al. A Car-Following Model Driven by Combination of Theory and Data Considering Effects of Lane Change of Side Cars [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(6): 10-19.
[14]	YE Feng, CHEN Biao, LAI Yizong. Contrastive Knowledge Distillation Method Based on Feature Space Embedding [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(5): 13-23.
[15]	MA Biyun, WU Gang, LIU Jiaojiao, et al. Low Complexity Blood Flow Velocity Estimation Algorithm via Sparse Pulse Sampling [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(5): 63-69.