面向无歧义旋转不变点云分析的4D局部建模与动态全局感知
4D Local Modeling Toward Dynamic Global Perception for Ambiguity-free Rotation-Invariant Point Cloud Analysis
提出将旋转等变几何表示转换为不变表示并融合全局姿态感知的框架，其可学习可转向变换和Bingham分布动态全局姿态参考可复用于点云分类/分割等任务，提升对对称或重复结构的判别力。
原文依据 Ga4DPF introduces a learnable steerable transform that equivariantly lifts point clouds into 4D space
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论旋转不变性仍是点云分析中的核心挑战，现有方法常受结构歧义和全局上下文不足的困扰。大多数旋转不变表示源自局部坐标系，本质上存在点对歧义，无法在对称或重复结构中捕获判别性特征，同时丢弃了有信息量的全局姿态线索。为克服这些局限，我们提出Ga4DPF，一种新颖的框架，通过将旋转等变几何表示转换为不变表示，同时融合全局姿态感知，提供鲁棒的、全局感知的旋转不变表示。具体而言，Ga4DPF引入可学习的可转向变换，将点云等变地提升到4D空间，促进鲁棒的局部特征构建并缓解点对歧义。同时，我们使用Bingham分布建模动态全局姿态参考，自适应地估计一致的全局旋转并增强全局特征判别性。在多个基准数据集上的大量实验表明，Ga4DPF以高计算效率实现了最优性能，为旋转不变点云分析提供了新范式。源代码见：https://github.com/jiaxunguo/ga4dpf。
英文原文摘要 1377 字符
Rotation invariance remains a core challenge in point cloud analysis, where existing methods often struggle with structural ambiguities and insufficient global context. Most rotation-invariant (RI) representations are derived from local coordinate systems, which inherently suffer from point-pair ambiguities and fail to capture discriminative features in symmetric or repetitive structures, while discarding informative global pose cues. To overcome these limitations, we propose Ga4DPF, a novel framework that offers a robust, global-aware RI representation by converting rotation-equivariant geometric representations into invariant ones, while concurrently integrating global pose awareness. Specifically, Ga4DPF introduces a learnable steerable transform that equivariantly lifts point clouds into 4D space, facilitating robust local feature construction and mitigating point-pair ambiguities. Concurrently, we model a dynamic global pose reference using the Bingham distribution, which adaptively estimates a consistent global rotation and enhances global feature discriminability. Extensive experiments on multiple benchmark datasets demonstrate that Ga4DPF achieves state-of-the-art performance with high computational efficiency, offering a new paradigm for rotation-invariant point cloud analysis. The source code is available at: https://github.com/jiaxunguo/ga4dpf.