Generalized Gaussian Entropy Model for Point Cloud Attribute Compression with Dynamic Likelihood Intervals

TL;DR

This paper introduces a generalized Gaussian entropy model with dynamic likelihood intervals for point cloud attribute compression, leveraging neural network estimated parameters for improved probability modeling and compression efficiency.

Contribution

It proposes a novel generalized Gaussian entropy model and a dynamic likelihood interval adjustment method, enhancing rate-distortion performance in point cloud compression.

Findings

Significant RD performance improvements on three VAE-based models.

Effective dynamic adjustment of likelihood intervals improves probability estimation.

Applicable to image and video compression tasks.

Abstract

Gaussian and Laplacian entropy models are proved effective in learned point cloud attribute compression, as they assist in arithmetic coding of latents. However, we demonstrate through experiments that there is still unutilized information in entropy parameters estimated by neural networks in current methods, which can be used for more accurate probability estimation. Thus we introduce generalized Gaussian entropy model, which controls the tail shape through shape parameter to more accurately estimate the probability of latents. Meanwhile, to the best of our knowledge, existing methods use fixed likelihood intervals for each integer during arithmetic coding, which limits model performance. We propose Mean Error Discriminator (MED) to determine whether the entropy parameter estimation is accurate and then dynamically adjust likelihood intervals. Experiments show that our method significantly improves rate-distortion (RD) performance on three VAE-based models for point cloud attribute compression, and our method can be applied to other compression tasks, such as image and video compression.