FLaTEC: Frequency-Disentangled Latent Triplanes for Efficient Compression of LiDAR Point Clouds

TL;DR

FLaTEC introduces a frequency-aware LiDAR point cloud compression method that decouples low- and high-frequency components, achieving high compression ratios and state-of-the-art rate-distortion performance.

Contribution

The paper presents a novel frequency-disentangling technique and hybridized latent triplanes for efficient, high-quality LiDAR point cloud compression.

Findings

Achieves 78% and 94% BD-rate reduction over standard codecs.

Outperforms existing methods in rate-distortion performance.

Reduces sparsity, computational cost, and storage requirements.

Abstract

Point cloud compression methods jointly optimize bitrates and reconstruction distortion. However, balancing compression ratio and reconstruction quality is difficult because low-frequency and high-frequency components contribute differently at the same resolution. To address this, we propose FLaTEC, a frequency-aware compression model that enables the compression of a full scan with high compression ratios. Our approach introduces a frequency-aware mechanism that decouples low-frequency structures and high-frequency textures, while hybridizing latent triplanes as a compact proxy for point cloud. Specifically, we convert voxelized embeddings into triplane representations to reduce sparsity, computational cost, and storage requirements. We then devise a frequency-disentangling technique that extracts compact low-frequency content while collecting high-frequency details across scales. The decoupled low-frequency and high-frequency components are stored in binary format. During decoding, full-spectrum signals are progressively recovered via a modulation block. Additionally, to compensate for the loss of 3D correlation, we introduce an efficient frequency-based attention mechanism that fosters local connectivity and outputs arbitrary resolution points. Our method achieves state-of-the-art rate-distortion performance and outperforms the standard codecs by 78\% and 94\% in BD-rate on both SemanticKITTI and Ford datasets.