Patch-Based Deep Autoencoder for Point Cloud Geometry Compression

TL;DR

This paper introduces a patch-based deep autoencoder for lossy point cloud geometry compression, dividing point clouds into patches for independent compression and achieving superior rate-distortion performance at low bitrates.

Contribution

It proposes a novel patch-based compression method with patch-to-patch training, improving compression efficiency and reconstruction quality over existing methods.

Findings

Outperforms state-of-the-art in rate-distortion at low bitrates

Ensures the same number of points after compression

Applicable to other point cloud reconstruction tasks

Abstract

The ever-increasing 3D application makes the point cloud compression unprecedentedly important and needed. In this paper, we propose a patch-based compression process using deep learning, focusing on the lossy point cloud geometry compression. Unlike existing point cloud compression networks, which apply feature extraction and reconstruction on the entire point cloud, we divide the point cloud into patches and compress each patch independently. In the decoding process, we finally assemble the decompressed patches into a complete point cloud. In addition, we train our network by a patch-to-patch criterion, i.e., use the local reconstruction loss for optimization, to approximate the global reconstruction optimality. Our method outperforms the state-of-the-art in terms of rate-distortion performance, especially at low bitrates. Moreover, the compression process we proposed can guarantee to generate the same number of points as the input. The network model of this method can be easily applied to other point cloud reconstruction problems, such as upsampling.