Generalized Gaussian Entropy Model for Point Cloud Attribute Compression with Dynamic Likelihood Intervals
This work addresses a specific bottleneck in point cloud compression, with potential applications to other compression tasks like image and video, but it is incremental as it builds on existing VAE-based methods.
The paper tackles the problem of inefficient entropy modeling in learned point cloud attribute compression by introducing a generalized Gaussian entropy model with dynamic likelihood intervals, resulting in significant improvements in rate-distortion performance on three VAE-based models.
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.