3D Point Cloud Attribute Compression Using Diffusion-Based Texture-Aware Intra Prediction
- 3 May 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (10) , 9633-9646
Abstract
There is an urgent need from various multimedia applications to efficiently compress point clouds. The Moving Picture Experts Group has released a standard platform called geometry-based point cloud compression (G-PCC). However, its k -nearest neighbor (k-NN) based attribute prediction has limited efficiency for point clouds with rich texture and directional information. To overcome this problem, we propose a texture-aware attribute predictive coding framework in a point cloud diffusion model. In our work, attribute intra prediction is solved as a diffusion-based interpolation problem, and a general attribute predictor is developed. It is theoretically proven that G-PCC k -NN based predictor is a degraded case of the proposed diffusion-based solution. First, a point cloud is represented as two levels of details with seeds as the inpainting mask and non-seed points to be predicted. Second, we design point cloud partial difference operators to perform energy-minimizing attribute inpainting from seeds to unknowns. Smooth attribute interpolation can be achieved via an iterative diffusion process, and an adaptive early termination is proposed to reduce complexity. Third, we propose a structure-adaptive attribute predictive coding scheme, where edge-enhancing anisotropic diffusion is employed to perform texture-aware attribute prediction. Finally, attributes of seeds are beforehand encoded and prediction residuals of left points are progressively encoded into bitstream. Experiments show the proposed scheme surpasses the state-of-the-art by an average of 14.14%, 17.52%, and 17.87% BD-BR gains on the coding of Y, U, and V components, respectively. Subjective results on attribute reconstruction quality also verify the advantage of our scheme.Keywords
Funding Information
- National Natural Science Foundation of China (62172021, 62271013, 62031013)
- Guangdong Province Pearl River Talent Program (2021QN020708)
- Shenzhen Science and Technology Program (JCYJ20230807120808017)
This publication has 39 references indexed in Scilit:
- RePaint: Inpainting using Denoising Diffusion Probabilistic Models2022
- Early Termination of Dyadic Region-Adaptive Hierarchical Transform for Efficient Attribute Compression of 3D Point CloudsIEEE Signal Processing Letters, 2021
- A Hybrid Compression Framework for Color Attributes of Static 3D Point CloudsIEEE Transactions on Circuits and Systems for Video Technology, 2021
- Multi-Scale Structured Dictionary Learning for 3-D Point Cloud Attribute CompressionIEEE Transactions on Circuits and Systems for Video Technology, 2020
- Predictive Generalized Graph Fourier Transform for Attribute Compression of Dynamic Point CloudsIEEE Transactions on Circuits and Systems for Video Technology, 2020
- 3D Point Cloud Attribute Compression via Graph PredictionIEEE Signal Processing Letters, 2020
- Applications of 3D point cloud data in the construction industry: A fifteen-year review from 2004 to 2018Advanced Engineering Informatics, 2019
- Understanding, Optimising, and Extending Data Compression with Anisotropic DiffusionInternational Journal of Computer Vision, 2014
- Edge-based compression of cartoon-like images with homogeneous diffusionPattern Recognition, 2011
- Image Compression with Anisotropic DiffusionJournal of Mathematical Imaging and Vision, 2008