Perceive More with Less: LiDAR Point Cloud Compression at Just Recognizable Distortion for 3D Scene Understanding
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (21) · 17778-17786
DOI: 10.1609/aaai.v40i21.38835 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Miaohui Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).
Abstract (Originalsprache)
Existing LiDAR point cloud (LPC) data coding methods primarily focus on balancing compression efficiency and reconstruction quality according to the human vision system (HVS). However, these methods rarely consider the requirements of downstream scene understanding tasks from the perspective of the machine vision system (MVS). To address this challenge, we explore the maximum degree of LPC compression that has negligible impact on perception accuracy, called LPC-based just recognizable compression distortion (lpcJRCD). Specifically, we introduce a novel point-wise quantization approach for constructing a MVS-based LiDAR dataset and present a new lpcJRCD-guided intelligent compression framework tailored for MVS applications. To enhance MVS-based LPC compression efficiency, we develop a dual-feature interaction (DFI) module that fuses point and voxel features. Additionally, we propose a mask-based loss function to ensure accurate point-wise quality level prediction. Experimental results demonstrate the effectiveness of our proposed model in reducing the average bit rate by up to 94.98% while preserving perception accuracy in autonomous vehicles.
Zitieren
APA
Wang, M., Huang, R., Liu, T., Lin, S., Liu, Y., & Song, Y. (2026). Perceive More with Less: LiDAR Point Cloud Compression at Just Recognizable Distortion for 3D Scene Understanding. Proceedings of the AAAI Conference on Artificial Intelligence, 40(21), 17778-17786. https://doi.org/10.1609/aaai.v40i21.38835
Vancouver
Wang M, Huang R, Liu T, Lin S, Liu Y, Song Y. Perceive More with Less: LiDAR Point Cloud Compression at Just Recognizable Distortion for 3D Scene Understanding. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(21):17778-17786. doi:10.1609/aaai.v40i21.38835
BibTeX
@article{Wang2026,
author = {Wang, Miaohui and Huang, Runnan and Liu, Taojun and Lin, Shuyuan and Liu, Ye and Song, Yun},
title = {Perceive More with Less: LiDAR Point Cloud Compression at Just Recognizable Distortion for 3D Scene Understanding},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {21},
pages = {17778--17786},
doi = {10.1609/aaai.v40i21.38835}
}
EUVIMED