Variable Rate Point Cloud Attribute Compression with Non-Local Attention Optimization

Point clouds are widely used as representations of 3D objects and scenes in a number of applications, including virtual and mixed reality, autonomous driving, antiques reconstruction. To reduce the cost for transmitting and storing such data, this paper proposes an end-to-end learning-based point cl...

Full description

Saved in:
Bibliographic Details
Published in:Applied sciences 2022-08, Vol.12 (16), p.8179
Main Authors: Huo, Xiao, Zhang, Saiping, Yang, Fuzheng
Format: Article
Language:English
Subjects:
Compression
Convolution
Deep learning
Efficiency
Geometry
Learning
Methods
Mixed reality
Neural networks
non-local attention mechanism
Optimization
Performance evaluation
point cloud
Software
sparse convolution
variable rate model
Video compression
Virtual reality
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Point clouds are widely used as representations of 3D objects and scenes in a number of applications, including virtual and mixed reality, autonomous driving, antiques reconstruction. To reduce the cost for transmitting and storing such data, this paper proposes an end-to-end learning-based point cloud attribute compression (PCAC) approach. The proposed network adopts a sparse convolution-based variational autoencoder (VAE) structure to compress the color attribute of point clouds. Considering the difficulty of stacked convolution operations in capturing long range dependencies, the attention mechanism is incorporated in which a non-local attention module is developed to capture the local and global correlations in both spatial and channel dimensions. Towards the practical application, an additional modulation network is offered to achieve the variable rate compression purpose in a single network, avoiding the memory cost of storing multiple networks for multiple bitrates. Our proposed method achieves state-of-the-art compression performance compared to other existing learning-based methods and further reduces the gap with the latest MPEG G-PCC reference software TMC13 version 14.
ISSN:2076-3417
2076-3417
DOI:10.3390/app12168179