DeepPCC: Learned Lossy Point Cloud Compression

doi:10.1109/TETCI.2024.3467192

DeepPCC: Learned Lossy Point Cloud Compression

2024-01-01

0

PRE

AI

DOI：10.1109/TETCI.2024.3467192

Original

Original request for help

Save

Abstract

En 中文

We propose DeepPCC, an end-to-end learning-based approach for the lossy compression of large-scale object point clouds. For both geometry and attribute components, we introduce the Multiscale Neighborhood Information Aggregation (NIA) mechanism, which applies resolution downscaling progressively (i.e., dyadic downsampling of geometry and average pooling of attribute) and combines sparse convolution and local self-attention at each resolution scale for effective feature representation. Under a simple autoencoder structure, scale-wise NIA blocks are stacked as the analysis and synthesis transform in the encoder-decoder pair to best characterize spatial neighbors for accurate approximation of geometry occupancy probability and attribute intensity. Experiments demonstrate that DeepPCC remarkably outperforms state-of-the-art rules-based MPEG G-PCC and learning-based solutions both quantitatively and qualitatively, providing strong evidence that DeepPCC is a promising solution for emerging AI-based PCC.

Keywords:

Point cloud compression

Geometry

Transform coding

Decoding

Entropy

Convolution

Standards

Image coding

Distortion

Correlation

geometry

attribute

sparse convolution

local self-attention

DeepPCC: Learned Lossy Point Cloud Compression

Abstract

Journal

Organization

Cited Papers