PCAC-GAN: A Sparse-Tensor-Based Generative Adversarial Network for 3D Point Cloud Attribute Compression

TL;DR

This paper introduces PCAC-GAN, a novel deep learning method using sparse convolutional GANs for efficient 3D point cloud attribute compression, outperforming existing learning-based methods and rivaling traditional standards.

Contribution

First application of GANs with sparse convolutions for point cloud attribute compression, combining adaptive voxel resolution selection for improved efficiency and quality.

Findings

Outperforms existing learning-based methods in attribute compression.

Rivals the latest G-PCC standard in visual quality.

Uses sparse tensors for computational efficiency.

Abstract

Learning-based methods have proven successful in compressing geometric information for point clouds. For attribute compression, however, they still lag behind non-learning-based methods such as the MPEG G-PCC standard. To bridge this gap, we propose a novel deep learning-based point cloud attribute compression method that uses a generative adversarial network (GAN) with sparse convolution layers. Our method also includes a module that adaptively selects the resolution of the voxels used to voxelize the input point cloud. Sparse vectors are used to represent the voxelized point cloud, and sparse convolutions process the sparse tensors, ensuring computational efficiency. To the best of our knowledge, this is the first application of GANs to compress point cloud attributes. Our experimental results show that our method outperforms existing learning-based techniques and rivals the latest G-PCC test model (TMC13v23) in terms of visual quality.