AnyPcc：用单一通用模型压缩任意点云
AnyPcc: Compressing Any Point Cloud with a Single Universal Model
面向点云几何压缩的通用上下文模型与实例自适应微调（IAFT）策略，可复用于任何需要跨密度、跨分布泛化的点云/3D 表征编码任务：把少量实例专属权重随码流传输，用极小码率换取几何压缩增益，这一「权重即侧信息」的思路也可迁移到 NeRF/高斯泼溅的压缩与传输。
原文依据 it fine-tunes a small subset of network weights and transmits them within the bitstream
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论泛化性仍是基于深度学习的点云几何压缩面临的关键挑战。现有方法在标准基准上表现良好，但在真实场景中性能急剧下降，原因在于两个根本性局限：缺乏能在多样数据密度下保持鲁棒的上下文模型，以及无法高效地适应分布外（OOD）数据。为同时克服这两项挑战，我们提出 AnyPcc，一个通用点云压缩框架。AnyPcc 首先采用通用上下文模型，利用粗粒度空间先验与细粒度通道先验，确保在整个密度谱上实现鲁棒的上下文建模。其次，我们提出的实例自适应微调（IAFT）策略通过协同显式与隐式压缩范式来处理 OOD 数据：对每个实例，它只微调网络权重的一小部分，并将这些权重在码流中传输；这些权重带来的极小码率开销被其在几何压缩上带来的增益显著抵消。在包含 15 个多样数据集的基准上进行的大量实验证实，AnyPcc 在保持低复杂度的同时，刷新了点云压缩的最优性能。我们的代码与数据集已发布，以鼓励可复现研究。
英文原文摘要 1307 字符
Generalization remains a critical challenge in deep learning-based point cloud geometry compression. While existing methods perform well on standard benchmarks, their performance collapses in real-world scenarios due to two fundamental limitations: the lack of context models that are robust across diverse data densities, and the inability to efficiently adapt to out-of-distribution (OOD) data. To overcome both challenges, we introduce AnyPcc, a universal point cloud compression framework. AnyPcc first employs a Universal Context Model that leverages coarse-grained spatial priors with fine-grained channel priors to ensure robust context modeling across the entire density spectrum. Second, our novel Instance-Adaptive Fine-Tuning (IAFT) strategy tackles OOD data by synergizing explicit and implicit compression paradigms. For each instance, it fine-tunes a small subset of network weights and transmits them within the bitstream. The minimal bitrate overhead from these weights is significantly outweighed by the resulting gains in geometry compression. Extensive experiments on a benchmark of 15 diverse datasets confirm that AnyPcc sets a new state-of-the-art in point cloud compression while maintaining low complexity. Our code and datasets have been released to encourage reproducible research.