Inter-LPCM: Learning-based Inter-Frame Predictive Coding for LiDAR Point Cloud Compression

TL;DR

This paper introduces Inter-LPCM, a learning-based inter-frame predictive coding method for LiDAR point cloud compression that leverages inter-frame correlations and specialized models for improved rate-distortion performance.

Contribution

It proposes novel inter-frame prediction models including Inter-RP and LAEP, and an RD-optimized quantization scheme tailored for spherical coordinate-based LiDAR data.

Findings

Achieves better rate-distortion performance than traditional methods.

Effectively captures complex motion and structural dependencies.

Source code is publicly available for reproducibility.

Abstract

Because LiDAR sensors acquire point clouds with a fixed angular resolution, the resulting data can be systematically parameterized and efficiently compressed in the spherical coordinate system. Traditional spherical coordinate-based point cloud compression methods have demonstrated strong rate-distortion (RD) performance, with the predictive geometry coding (PredGeom) method in the geometry-based point cloud compression (G-PCC) standard being a prominent example. Although PredGeom includes an inter-frame prediction mode, it relies on a simple linear model, which limits its ability to capture complex motion patterns and structural dependencies. Meanwhile, existing learning-based compression methods in the spherical domain do not exploit inter-frame correlations to reduce geometry redundancy. To address these limitations, we propose a learning-based inter-frame predictive coding method, termed Inter-LPCM. For azimuth prediction, we employ a delta coding strategy based on the predefined angular resolution. To improve radius compression, we introduce an inter-frame radius predictive (Inter-RP) model that estimates the current point's radius using neighboring points from both the current frame and the registered reference frame. In addition, we design a lightweight attention-based prediction (LAEP) model to predict elevation angles by capturing long-range geometric correlations across different coordinates. For quantization, we propose an RD-optimized method to select quantization steps in the spherical coordinate system. For entropy coding, we design distinct models for each spherical coordinate component. These models are adapted to the statistical priors of each coordinate, enabling more accurate probability estimation. Our source code is publicly available at https://github.com/SDUChangSun/Inter-LPCM