通过融合时空相关性，实现高速点云序列压缩。
Hint: hierarchical inter-frame correlation for one-shot point cloud sequence compression
- 利用前帧存在图与邻域查找构建时序特征，结合空间特征进行编码。
- 编码解码时间分别仅需105毫秒和140毫秒，比G-PCC快49.6倍和21.6倍。
- 适用于实时点云传输场景，尤其适合对延迟敏感的应用。
深度学习在点云压缩中展现出强大能力，其中无损压缩的熵建模受到广泛关注。然而，多数方法仅依赖父节点/兄弟节点上下文和逐层自回归，导致解码延迟高达10^1至10^2秒。本文提出HINT，一种融合时序与空间相关性的点云序列压缩方法。首先通过两阶段时序特征提取：(i) 父层级存在图，(ii) 子层级前一帧邻域查询。这些线索通过逐元素加法与空间特征融合，并采用分组策略编码。实验结果表明，HINT的编码与解码时间分别为105毫秒和140毫秒，相较G-PCC分别提速49.6倍和21.6倍，同时实现最高达43.6%的码率降低，持续优于仅用空间信息的基线方法RENO。
原文摘要 · Abstract (English)
Deep learning has demonstrated strong capability in compressing point clouds. Within this area, entropy modeling for lossless compression is widely investigated. However, most methods rely solely on parent/sibling contexts and level-wise autoregression, which suffers from decoding latency on the order of 10^1-10^2 seconds. We propose HINT, a method that integrates temporal and spatial correlation for sequential point cloud compression. Specifically, it first uses a two-stage temporal feature extraction: (i) a parent-level existence map and (ii) a child-level neighborhood lookup in the previous frame. These cues are fused with the spatial features via element-wise addition and encoded with a group-wise strategy. Experimental results show that HINT achieves encoding and decoding time at 105 ms and 140 ms, respectively, equivalent to 49.6x and 21.6x acceleration in comparison with G-PCC, while achieving up to 43.6% bitrate reduction and consistently outperforming the spatial-only baseline (RENO).
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。