PointCNN++：在原生点上执行高性能卷积
PointCNN++: Performant Convolution on Native Points
把稀疏卷积从体素推广到原始高精度点坐标，并以 MVMR 形式实现专用 GPU kernel，可直接替换体素骨干用于点云配准等需要几何精度的任务，兼顾显存与速度。
原文依据 It generalizes sparse convolution from voxels to points, treating voxel-based convolution as a specialized, degraded case
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现有的三维点云卷积学习方法分为两种范式：基于点的方法保留了几何精度，但往往面临性能挑战；基于体素的方法通过量化获得高效率，却牺牲了几何保真度。这种精度损失是点云配准等任务的关键瓶颈。我们提出 PointCNN++，一种全新的架构设计，从根本上缓解精度与性能之间的权衡。它将稀疏卷积从体素推广到点，把基于体素的卷积视为我们更通用的基于点的卷积的一个特化、退化情形。首先，我们引入以点为中心的卷积，其感受野以原始的高精度点坐标为中心。其次，为使这一高保真操作具备良好性能，我们设计了一种直接在点上运算的计算策略。我们将原生点上的卷积形式化为矩阵-向量乘与归约（MVMR）问题，并为此开发了专用的、高度优化的 GPU kernel。实验表明，PointCNN++ 的显存占用比代表性基于点的方法低一个数量级，速度也快数倍。此外，当它作为其所推广的基于体素骨干网络的简单替代品使用时，显著提升了点云配准精度，同时显存更省、速度更快。PointCNN++ 表明，保留几何细节与实现高性能并非互斥，为高保真、高效率的新一类三维学习铺平了道路。
英文原文摘要 1657 字符
Existing convolutional learning methods for 3D point cloud data are divided into two paradigms: point-based methods that preserve geometric precision but often face performance challenges, and voxel-based methods that achieve high efficiency through quantization at the cost of geometric fidelity. This loss of precision is a critical bottleneck for tasks such as point cloud registration. We propose PointCNN++, a novel architectural design that fundamentally mitigates this precision-performance trade-off. It generalizes sparse convolution from voxels to points, treating voxel-based convolution as a specialized, degraded case of our more general point-based convolution. First, we introduce a point-centric convolution where the receptive field is centered on the original, high-precision point coordinates. Second, to make this high-fidelity operation performant, we design a computational strategy that operates natively on points. We formulate the convolution on native points as a Matrix-Vector Multiplication and Reduction (MVMR) problem, for which we develop a dedicated, highly-optimized GPU kernel. Experiments demonstrate that PointCNN++ uses an order of magnitude less memory and is several times faster than representative point-based methods. Furthermore, when used as a simple replacement for the voxel-based backbones it generalizes, it significantly improves point cloud registration accuracies while proving both more memory-efficient and faster. PointCNN++ shows that preserving geometric detail and achieving high performance are not mutually exclusive, paving the way for a new class of 3D learning with high fidelity and efficiency.