Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhu, Jiahao, You, Kang, Ding, Dandan, Ma, Zhan
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2605.01320
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914526189846528
author Zhu, Jiahao
You, Kang
Ding, Dandan
Ma, Zhan
author_facet Zhu, Jiahao
You, Kang
Ding, Dandan
Ma, Zhan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_01320
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PACE: Post-Causal Entropy Modeling for Learned LiDAR Point Cloud Compression
Zhu, Jiahao
You, Kang
Ding, Dandan
Ma, Zhan
Computer Vision and Pattern Recognition
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.
title PACE: Post-Causal Entropy Modeling for Learned LiDAR Point Cloud Compression
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.01320