Deep Geometry Post-Processing for Decompressed Point Clouds

04/29/2022
by   Xiaoqing Fan, et al.
0

Point cloud compression plays a crucial role in reducing the huge cost of data storage and transmission. However, distortions can be introduced into the decompressed point clouds due to quantization. In this paper, we propose a novel learning-based post-processing method to enhance the decompressed point clouds. Specifically, a voxelized point cloud is first divided into small cubes. Then, a 3D convolutional network is proposed to predict the occupancy probability for each location of a cube. We leverage both local and global contexts by generating multi-scale probabilities. These probabilities are progressively summed to predict the results in a coarse-to-fine manner. Finally, we obtain the geometry-refined point clouds based on the predicted probabilities. Different from previous methods, we deal with decompressed point clouds with huge variety of distortions using a single model. Experimental results show that the proposed method can significantly improve the quality of the decompressed point clouds, achieving 9.30dB BDPSNR gain on three representative datasets on average.

READ FULL TEXT
research
12/20/2019

A Comprehensive Study and Comparison of Core Technologies for MPEG 3D Point Cloud Compression

Point cloud based 3D visual representation is becoming popular due to it...
research
07/10/2020

Progressive Point Cloud Deconvolution Generation Network

In this paper, we propose an effective point cloud generation method, wh...
research
03/17/2022

3DAC: Learning Attribute Compression for Point Clouds

We study the problem of attribute compression for large-scale unstructur...
research
03/12/2023

PointPatchMix: Point Cloud Mixing with Patch Scoring

Data augmentation is an effective regularization strategy for mitigating...
research
05/02/2023

Geometric Prior Based Deep Human Point Cloud Geometry Compression

The emergence of digital avatars has raised an exponential increase in t...
research
12/01/2021

Attribute Artifacts Removal for Geometry-based Point Cloud Compression

Geometry-based point cloud compression (G-PCC) can achieve remarkable co...
research
05/10/2023

SHS-Net: Learning Signed Hyper Surfaces for Oriented Normal Estimation of Point Clouds

We propose a novel method called SHS-Net for oriented normal estimation ...

Please sign up or login with your details

Forgot password? Click here to reset