LVAC: Learned Volumetric Attribute Compression for Point Clouds using Coordinate Based Networks

TL;DR

This paper introduces LVAC, a novel neural network-based method for compressing point cloud attributes by modeling them as volumetric functions, outperforming traditional methods like RAHT.

Contribution

It is the first to compress volumetric functions using local coordinate-based neural networks, integrating hierarchical transform coefficients for improved compression.

Findings

Outperforms RAHT by 2-4 dB in rate-distortion performance.

Uses a novel auto-decoder framework with neural networks for attribute compression.

Potential applicability to neural radiance field compression.

Abstract

We consider the attributes of a point cloud as samples of a vector-valued volumetric function at discrete positions. To compress the attributes given the positions, we compress the parameters of the volumetric function. We model the volumetric function by tiling space into blocks, and representing the function over each block by shifts of a coordinate-based, or implicit, neural network. Inputs to the network include both spatial coordinates and a latent vector per block. We represent the latent vectors using coefficients of the region-adaptive hierarchical transform (RAHT) used in the MPEG geometry-based point cloud codec G-PCC. The coefficients, which are highly compressible, are rate-distortion optimized by back-propagation through a rate-distortion Lagrangian loss in an auto-decoder configuration. The result outperforms RAHT by 2--4 dB. This is the first work to compress volumetric functions represented by local coordinate-based neural networks. As such, we expect it to be applicable beyond point clouds, for example to compression of high-resolution neural radiance fields.