PACE: Post-Causal Entropy Modeling for Learned LiDAR Point Cloud Compression

TL;DR

PACE introduces a flexible, low-latency LiDAR point cloud compression framework that separates context aggregation from probability prediction, enabling efficient, adaptable encoding with state-of-the-art results.

Contribution

It reformulates ancestral context aggregation as a non-causal backbone and confines causality to a lightweight predictor, improving efficiency and adaptability.

Findings

Achieves state-of-the-art compression efficiency with significant BD-BR savings.

Reduces decoding latency by over 90% in autoregressive mode.

Supports multiple prediction stages for flexible performance-latency trade-offs.

Abstract

LiDAR point cloud compression is vital for autonomous systems to handle massive data from high-resolution sensors. While learned entropy modeling built upon octree structures yields high compression gains, it faces two critical bottlenecks: 1) prohibitive latency, particularly during decoding, caused by causal, multi-stage context modeling; and 2) a rigid performance-latency trade-off, preventing a single model from adapting to varying constraints. These limitations stem from the tight coupling between context aggregation backbone and probability prediction. To address this, we propose PACE, a new framework that reformulates ancestral context aggregation as a non-causal backbone and confines causality to a lightweight, stage-scalable predictor, eliminating repetitive backbone executions and reducing computational overhead. The predictor supports an arbitrary number of prediction stages, supporting seamless adaptation across diverse performance-latency trade-offs without reloading parameters. Experiments demonstrate that PACE sets a new state-of-the-art in compression efficiency, achieving notable BD-BR savings and reducing decoding latency by over 90% in autoregressive mode, highly attractive for practical applications.