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

2026-05-18

AI Summary

Existing LiDAR point cloud compression methods struggle to effectively model inter-frame motion and structural dependencies in spherical coordinates, leading to insufficient removal of geometric redundancy. This work proposes the first learning-based inter-frame predictive coding framework tailored for spherical coordinates, which jointly leverages the current frame and a registered reference frame to enable efficient prediction of radius, azimuth, and elevation components. The approach introduces a lightweight attention mechanism to capture long-range geometric correlations, designs an inter-frame radius predictor combined with delta encoding, and integrates rate-distortion-optimized quantization with component-adaptive entropy coding. Experimental results demonstrate that the proposed method significantly outperforms existing techniques such as PredGeom in rate-distortion performance, with code publicly released.

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

Problem

• LiDAR point cloud compression
• inter-frame prediction
• spherical coordinate system
• geometry redundancy
• rate-distortion performance

Innovation

• Inter-frame prediction
• Learning-based compression
• Spherical coordinate system
• Attention mechanism
• LiDAR point cloud