3DAC: Learning Attribute Compression for Point Clouds
Authors:
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 14799-14808
Abstract
We study the problem of attribute compression for large-scale unstructured 3D point clouds. Through an in-depth exploration of the relationships between different encoding steps and different attribute channels, we introduce a deep compression network, termed 3DAC, to explicitly compress the attributes of 3D point clouds and reduce storage usage in this paper. Specifically, the point cloud attributes such as color and reflectance are firstly converted to transform coefficients. We then propose a deep entropy model to model the probabilities of these coefficients by considering information hidden in attribute transforms and previous encoded attributes. Finally, the estimated probabilities are used to further compress these transform coefficients to a final attributes bitstream. Extensive experiments conducted on both indoor and outdoor large-scale open point cloud datasets, including ScanNet and SemanticKITTI, demonstrated the superior compression rates and reconstruction quality of the proposed method.Keywords
Funding Information
- National Natural Science Foundation of China (U20A20185,61972435,61971282)
- Natural Science Foundation of Guangdong Province (2022B1515020103)
- China Scholarship Council (CSC)
This publication has 43 references indexed in Scilit:
- Point cloud attribute compression with graph transform2014
- Towards 3D Point cloud based object maps for household environmentsRobotics and Autonomous Systems, 2008
- Adaptive Run-Length / Golomb-Rice Encoding of Quantized Generalized Gaussian Sources with Unknown Statistics2006
- Virtual reality and mixed reality for virtual learning environmentsComputers & Graphics, 2006
- Theoretical foundations of transform codingIEEE Signal Processing Magazine, 2001
- The LOCO-I lossless image compression algorithm: principles and standardization into JPEG-LSIEEE Transactions on Image Processing, 2000
- The JPEG still picture compression standardIEEE Transactions on Consumer Electronics, 1992
- Arithmetic coding for data compressionCommunications of the ACM, 1987
- Geometric modeling using octree encodingComputer Graphics and Image Processing, 1982
- A Mathematical Theory of CommunicationBell System Technical Journal, 1948