ELiC：基于跨位深特征传播与编码器袋的高效激光雷达几何压缩
ELiC: Efficient LiDAR Geometry Compression via Cross-Bit-depth Feature Propagation and Bag-of-Encoders
提出跨位深特征传播和Bag-of-Encoders选择机制，可复用于其他层次化点云压缩或占用预测任务，提升实时压缩效率。
原文依据 Cross-bit-depth propagation reuses features extracted at denser, lower depths to support prediction at sparser, higher depths.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论层次化激光雷达几何压缩从低位深到高位深编码体素占用，然而先前方法独立处理每个深度层，并在每一层从坐标重新估计局部上下文，限制了压缩效率。我们提出ELiC，一个实时框架，结合了跨位深特征传播、编码器袋（BoE）选择方案以及保持莫顿序的层次结构。跨位深传播复用从更密集的低深度层提取的特征，以支持更稀疏的高深度层的预测。BoE在每个深度层从一个小型池中选择最合适的编码网络，根据观测到的占用统计自适应调整容量，而无需为每一层训练单独的模型。莫顿层次结构在深度转换间保持全局Z序，消除了逐层排序并降低了延迟。这些组件共同改进了熵建模和计算效率，在Ford和SemanticKITTI数据集上以实时吞吐量实现了最优压缩。代码和预训练模型可在http://github.com/moolgom/ELiCv1获取。
英文原文摘要 1086 字符
Hierarchical LiDAR geometry compression encodes voxel occupancies from low to high bit-depths, yet prior methods treat each depth independently and re-estimate local context from coordinates at every level, limiting compression efficiency. We present ELiC, a real-time framework that combines cross-bit-depth feature propagation, a Bag-of-Encoders (BoE) selection scheme, and a Morton-order-preserving hierarchy. Cross-bit-depth propagation reuses features extracted at denser, lower depths to support prediction at sparser, higher depths. BoE selects, per depth, the most suitable coding network from a small pool, adapting capacity to observed occupancy statistics without training a separate model for each level. The Morton hierarchy maintains global Z-order across depth transitions, eliminating per-level sorting and reducing latency. Together these components improve entropy modeling and computation efficiency, yielding state-of-the-art compression at real-time throughput on Ford and SemanticKITTI. Code and pretrained models are available at http://github.com/moolgom/ELiCv1.