Volumetric 3D Point Cloud Attribute Compression: Learned polynomial bilateral filter for prediction

2023/11/22 by Tam Thuc Do, Do, Tam Thuc, Philip A. Chou +3
Engineering · Medicine · #3D Shape Modeling and Analysis #Advanced Numerical Analysis Techniques #FOS: Electrical engineering #Medical Imaging Techniques and Applications #Signal Processing (eess.SP) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2311.13533

openalex publication_date 2023/11/22 · openalex created_date 2023/11/24 · openalex updated_date 2026/07/28

Abstract

We extend a previous study on 3D point cloud attribute compression scheme that uses a volumetric approach: given a target volumetric attribute function f : ℝ³ ↦ ℝ, we quantize and encode parameters θ that characterize f at the encoder, for reconstruction f_θ(\mathbf(x)) at known 3D points \mathbf(x) at the decoder. Specifically, parameters θ are quantized coefficients of B-spline basis vectors \mathbfΦ_l (for order p ≥ 2) that span the function space F_l^(p) at a particular resolution l, which are coded from coarse to fine resolutions for scalability. In this work, we focus on the prediction of finer-grained coefficients given coarser-grained ones by learning parameters of a polynomial bilateral filter (PBF) from data. PBF is a pseudo-linear filter that is signal-dependent with a graph spectral interpretation common in the graph signal processing (GSP) field. We demonstrate PBF's predictive performance over a linear predictor inspired by MPEG standardization over a wide range of point cloud datasets.

Related

• Learned Nonlinear Predictor for Critically Sampled 3D Point Cloud Attribute Compression
• Volumetric Attribute Compression for 3D Point Clouds using Feedforward Network with Geometric Attention
• Deep Unrolling of Sparsity-Induced RDO for 3D Point Cloud Attribute Coding
• Multi-resolution intra-predictive coding of 3D point cloud attributes
• LVAC: Learned Volumetric Attribute Compression for Point Clouds using Coordinate Based Networks