Hierarchical Distortion Learning for Fast Lossy Compression of Point Clouds
- 30 April 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 6031-6046
Abstract
The growth of 3D point cloud applications requires efficient compression techniques for high-quality and low-latency services. Recently, learning-based point cloud compression models have made significant progress. However, geometric distortion resulting from downsampling limits the feature depth within large-scale point clouds, thereby constraining the receptive field and suppressing the redundant removal. Moreover, the issues of computational efficiency and reconstruction quality still persist in the compression of large-scale point clouds. To address these challenges, we propose a hierarchical distortion learning framework for end-to-end lossy compression of point clouds. First, we design a feature residual compression module to efficiently transmit shallow semantics between the encoder and the decoder, which enables a lightweight design of our framework. Second, we introduce a geometry residual compression module to progressively complement the reconstruction distortion, avoiding the accumulation of geometric distortion. By integrating these two modules and employing sufficient downsampling processes, we develop a high-performance framework with a significantly enlarged receptive field and low computational cost. Extensive experiments demonstrate that our method achieves state-ofthe- art performance in geometry lossy compression, while delivering competitive performance in joint geometry and color lossy compression with fast running speed. Code is available at https://github.com/pengpeng-yu/FastPCC.Keywords
Funding Information
- National Natural Science Foundation of China (U20A20185)
- Basic and Applied Basic Research Foundation of Guangdong Province (2022B1515020103and, 2023B1515120087)
- Shenzhen Science and Technology Program (RCYX20200714114641140)
- Major Key Project of PCL
This publication has 50 references indexed in Scilit:
- 3DAC: Learning Attribute Compression for Point Clouds2022
- VoxelContext-Net: An Octree based Framework for Point Cloud Compression2021
- Generative Sparse Detection Networks for 3D Single-Shot Object Detection2020
- OctSqueeze: Octree-Structured Entropy Model for LiDAR Compression2020
- Learned Image Compression With Discretized Gaussian Mixture Likelihoods and Attention Modules2020
- 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks2019
- Practical Full Resolution Learned Lossless Image Compression2019
- Full Resolution Image Compression with Recurrent Neural Networks2017
- Are we ready for autonomous driving? The KITTI vision benchmark suite2012
- The JPEG 2000 still image compression standardIEEE Signal Processing Magazine, 2001