提出轻量级框架，实现激光雷达点云的实时无损压缩。
Towards Practical Lossless Neural Compression for LiDAR Point Clouds
- 通过迭代重稠密化与跨尺度特征传播，高效建模稀疏几何结构。
- 在真实场景下达到实时压缩速度，压缩率优于现有方法。
- 全整数推理确保跨平台一致性，适合工业部署。
激光雷达点云在诸多应用中至关重要，但高精度几何细节的极端稀疏性阻碍了有效上下文建模，限制了现有方法的压缩速度与性能。为此，我们提出一种紧凑表示，用于高效的预测式无损编码。框架包含两个轻量模块：首先，几何重稠密化模块迭代地对编码后的稀疏几何进行重稠密化，以密集尺度提取特征，再对特征进行稀疏化以支持预测编码；该模块避免在高度稀疏细节上进行高开销计算，同时保持轻量预测头。其次，跨尺度特征传播模块利用多分辨率层级的占用提示，引导分层特征传播，实现跨尺度信息共享，减少冗余特征提取。此外，我们引入纯整数推理流程，实现比特级跨平台一致性，避免现有神经压缩方法中的熵编码崩溃问题，并进一步加速编码过程。实验表明，该方法在真实场景下实现具有竞争力的压缩性能与实时速度。代码将在论文接受后公开，地址：https://github.com/pengpeng-yu/FastPCC。
原文摘要 · Abstract (English)
LiDAR point clouds are fundamental to various applications, yet the extreme sparsity of high-precision geometric details hinders efficient context modeling, thereby limiting the compression speed and performance of existing methods. To address this challenge, we propose a compact representation for efficient predictive lossless coding. Our framework comprises two lightweight modules. First, the Geometry Re-Densification Module iteratively densifies encoded sparse geometry, extracts features at a dense scale, and then sparsifies the features for predictive coding. This module avoids costly computation on highly sparse details while maintaining a lightweight prediction head. Second, the Cross-scale Feature Propagation Module leverages occupancy cues from multiple resolution levels to guide hierarchical feature propagation, enabling information sharing across scales and reducing redundant feature extraction. Additionally, we introduce an integer-only inference pipeline to enable bit-exact cross-platform consistency, which avoids the entropy-coding collapse observed in existing neural compression methods and further accelerates coding. Experiments demonstrate competitive compression performance at real-time speed. Code will be released upon acceptance. Code is available at https://github.com/pengpeng-yu/FastPCC.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。