Deep Learning-Based Joint Geometry and Attribute Up-Sampling for Large-Scale Colored Point Clouds
IEEE Transactions on Image Processing · 2026 · 35 · 1305-1320
DOI: 10.1109/tip.2026.3657214 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Yun Zhang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 41 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shenzhen Key Science and Technology Program, Natural Science Foundation of Guangdong Province.
Abstract (Originalsprache)
Colored point cloud comprising geometry and attribute components is one of the mainstream representations enabling realistic and immersive 3D applications. To generate large-scale and denser colored point clouds, we propose a deep learning-based Joint Geometry and Attribute Up-sampling (JGAU) method, which learns to model both geometry and attribute patterns and leverages the spatial attribute correlation. Firstly, we establish and release a large-scale dataset for colored point cloud up-sampling, named SYSU-PCUD, which has 121 large-scale colored point clouds with diverse geometry and attribute complexities in six categories and four sampling rates. Secondly, to improve the quality of up-sampled point clouds, we propose a deep learning-based JGAU framework to up-sample the geometry and attribute jointly. It consists of a geometry up-sampling network and an attribute up-sampling network, where the latter leverages the up-sampled auxiliary geometry to model neighborhood correlations of the attributes. Thirdly, we propose two coarse attribute up-sampling methods, Geometric Distance Weighted Attribute Interpolation (GDWAI) and Deep Learning-based Attribute Interpolation (DLAI), to generate coarsely up-sampled attributes for each point. Then, we propose an attribute enhancement module to refine the up-sampled attributes and generate high quality point clouds by further exploiting intrinsic attribute and geometry patterns. Extensive experiments show that Peak Signal-to-Noise Ratio (PSNR) achieved by the proposed JGAU are 33.90 dB, 32.10 dB, 31.10 dB, and 30.39 dB when up-sampling rates are $4\times $ , $8\times $ , $12\times $ , and $16\times $ , respectively. Compared to the state-of-the-art schemes, the JGAU achieves an average of 2.32 dB, 2.47 dB, 2.28 dB and 2.11 dB PSNR gains at four up-sampling rates, respectively, which are significant. The code is released with https://github.com/SYSU-Video/JGAU.
Förderung
- National Natural Science Foundation of China
- Shenzhen Key Science and Technology Program
- Natural Science Foundation of Guangdong Province
- Shenzhen–Hong Kong Collaborative Project Tier-A
- Hong Kong GRF-RGC General Research Fund
- Shenzhen Natural Science Foundation
- Research Grants Council of the Hong Kong Special Administrative Region, China
Zitieren
APA
Zhang, Y., Chen, F., Li, N., Guo, Z., Wang, X., Miao, F., & Kwong, S. (2026). Deep Learning-Based Joint Geometry and Attribute Up-Sampling for Large-Scale Colored Point Clouds. IEEE Transactions on Image Processing, 35, 1305-1320. https://doi.org/10.1109/tip.2026.3657214
Vancouver
Zhang Y, Chen F, Li N, Guo Z, Wang X, Miao F, et al. Deep Learning-Based Joint Geometry and Attribute Up-Sampling for Large-Scale Colored Point Clouds. IEEE Transactions on Image Processing. 2026;35:1305-1320. doi:10.1109/tip.2026.3657214
BibTeX
@article{Zhang2026,
author = {Zhang, Yun and Chen, Feifan and Li, Na and Guo, Zhiwei and Wang, Xu and Miao, Fen and Kwong, Sam},
title = {Deep Learning-Based Joint Geometry and Attribute Up-Sampling for Large-Scale Colored Point Clouds},
journal = {IEEE Transactions on Image Processing},
year = {2026},
volume = {35},
pages = {1305--1320},
doi = {10.1109/tip.2026.3657214}
}
EUVIMED