GQE-Net: A Graph-based Quality Enhancement Network for Point Cloud Color Attribute

dc.contributor.authorXing, Jinrui
dc.contributor.authorYuan, Hui
dc.contributor.authorHamzaoui, Raouf
dc.contributor.authorLiu, Hao
dc.contributor.authorHou, Junhui
dc.date.acceptance2023-10-31
dc.date.accessioned2023-11-02T11:58:11Z
dc.date.available2023-11-02T11:58:11Z
dc.date.issued2023-10-31
dc.descriptionThe file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link.
dc.description.abstractIn recent years, point clouds have become increasingly popular for representing three-dimensional (3D) visual objects and scenes. To efficiently store and transmit point clouds, compression methods have been developed, but they often result in a degradation of quality. To reduce color distortion in point clouds, we propose a graph-based quality enhancement network (GQE-Net) that uses geometry information as an auxiliary input and graph convolution blocks to extract local features efficiently. Specifically, we use a parallel-serial graph attention module with a multi-head graph attention mechanism to focus on important points or features and help them fuse together. Additionally, we design a feature refinement module that takes into account the normals and geometry distance between points. To work within the limitations of GPU memory capacity, the distorted point cloud is divided into overlap-allowed 3D patches, which are sent to GQE-Net for quality enhancement. To account for differences in data distribution among different color components, three models are trained for the three color components. Experimental results show that our method achieves state-of-the-art performance. For example, when implementing GQE-Net on a recent test model of the geometry-based point cloud compression (G-PCC) standard, 0.43 dB, 0.25 dB and 0.36 dB Bjϕntegaard delta (BD)-peak signal-to-noise ratio (PSNR), corresponding to 14.0%, 9.3% and 14.5% BD-rate savings were achieved on dense point clouds for the Y, Cb, and Cr components, respectively. The source code of our method is available at https://github.com/xjr998/GQE-Net.
dc.funderOther external funder (please detail below)
dc.funder.otherNational Natural Science Foundation of China
dc.funder.otherTaishan Scholar Project of Shandong Province
dc.funder.otherNatural Science Foundation of Shandong Province
dc.funder.otherCentral Guidance Fund for Local Science and Technology Development of Shandong Province
dc.funder.otherHigh-end Foreign Experts Recruitment Plan of the Chinese Ministry of Science and Technology
dc.funder.otherHong Kong Research Grants Council
dc.funder.otherOPPO Research Fund
dc.identifier.citationXing, J., Yuan, H., Hamzaoui, R., Liu, H. and Hou, J. (2023) GQE-Net: A graph-based quality enhancement network for point cloud color attribute, IEEE Transactions on Image Processing,
dc.identifier.doihttps://doi.org/10.1109/TIP.2023.3330086
dc.identifier.urihttps://hdl.handle.net/2086/23319
dc.language.isoen
dc.peerreviewedYes
dc.publisherIEEE
dc.researchinstituteInstitute of Engineering Sciences (IES)
dc.rightsAttribution-NonCommercial-NoDerivs 2.0 UK: England & Walesen
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/2.0/uk/
dc.subjectPoint clouds
dc.subjectQuality enhancement
dc.subjectGraph neural network
dc.subjectG-PCC
dc.titleGQE-Net: A Graph-based Quality Enhancement Network for Point Cloud Color Attribute
dc.typeArticle

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
GQE-Net_A Graph-based Quality Enhancement Network for Point Cloud Color Attribute.pdf
Size:
6.24 MB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
4.2 KB
Format:
Item-specific license agreed upon to submission
Description: