Recently MLP-based methods have shown strong performance in point cloud analysis. Simple MLP architectures are able to learn geometric features in local point groups yet fail to model long-range dependencies directly. In this paper, we propose Point Deformable Network (PDNet), a concise MLP-based network that can capture long-range relations with strong representation ability. Specifically, we put forward Point Deformable Aggregation Module (PDAM) to improve representation capability in both long-range dependency and adaptive aggregation among points. For each query point, PDAM aggregates information from deformable reference points rather than points in limited local areas. The deformable reference points are generated data-dependent, and we initialize them according to the input point positions. Additional offsets and modulation scalars are learned on the whole point features, which shift the deformable reference points to the regions of interest. We also suggest estimating the normal vector for point clouds and applying Enhanced Normal Embedding (ENE) to the geometric extractors to improve the representation ability of single-point. Extensive experiments and ablation studies on various benchmarks demonstrate the effectiveness and superiority of our PDNet.

翻译：近期，基于多层感知机（MLP）的方法在点云分析中展现出强劲性能。简单的MLP架构能够学习局部点群的几何特征，但无法直接建模长距离依赖关系。本文提出了一种简洁的MLP网络——点可变形网络（PDNet），该网络能够捕获长距离关系并具备强表征能力。具体而言，我们提出了点可变形聚合模块（PDAM），旨在同时提升点间的长距离依赖与自适应聚合的表征能力。对于每个查询点，PDAM从可变形参考点（而非局部受限区域内的点）聚合信息。这些可变形参考点是数据依赖生成的，并根据输入点位置进行初始化。此外，网络在全局点特征上学习额外的偏移量与调制标量，从而将可变形参考点迁移至感兴趣区域。我们还提出为点云估计法向量，并将增强法向量嵌入（ENE）应用于几何特征提取器，以提升单点的表征能力。在多种基准数据集上的广泛实验与消融研究表明，我们提出的PDNet具有有效性与优越性。