论文标题
重新思考网络设计和点云中的本地几何形状：一个简单的残差MLP框架
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework
论文作者
论文摘要
由于不规则性和无序的数据结构，点云分析具有挑战性。为了捕获3D几何形状，先前的作品主要依赖于使用卷积，图形或注意机制探索复杂的局部几何提取器。但是，这些方法在推理过程中会产生不利的延迟，并且在过去几年中的性能饱和。在本文中，我们介绍了有关此任务的新颖观点。我们注意到，详细的本地几何信息可能不是点云分析的关键 - 我们引入了一个纯粹的残留MLP网络，称为PointMLP，该网络没有集成复杂的局部几何提取器，但仍表现非常竞争。 PointMLP配备了建议的轻量级几何仿射模块，可在多个数据集上提供新的最新最新技术。在现实世界中的Scanobjectnn数据集上，我们的方法甚至超过了3.3％的精度。我们强调，PointMLP在没有任何复杂操作的情况下实现了这种强大的性能，因此导致了卓越的推理速度。与最新的司法机相比，PointMLP训练2倍，测试7倍，并且在ModelNet40基准测试上更准确。我们希望我们的指数可以帮助社区更好地了解点云分析。该代码可在https://github.com/ma-xu/pointmlp-pytorch上找到。
Point cloud analysis is challenging due to irregularity and unordered data structure. To capture the 3D geometries, prior works mainly rely on exploring sophisticated local geometric extractors using convolution, graph, or attention mechanisms. These methods, however, incur unfavorable latency during inference, and the performance saturates over the past few years. In this paper, we present a novel perspective on this task. We notice that detailed local geometrical information probably is not the key to point cloud analysis -- we introduce a pure residual MLP network, called PointMLP, which integrates no sophisticated local geometrical extractors but still performs very competitively. Equipped with a proposed lightweight geometric affine module, PointMLP delivers the new state-of-the-art on multiple datasets. On the real-world ScanObjectNN dataset, our method even surpasses the prior best method by 3.3% accuracy. We emphasize that PointMLP achieves this strong performance without any sophisticated operations, hence leading to a superior inference speed. Compared to most recent CurveNet, PointMLP trains 2x faster, tests 7x faster, and is more accurate on ModelNet40 benchmark. We hope our PointMLP may help the community towards a better understanding of point cloud analysis. The code is available at https://github.com/ma-xu/pointMLP-pytorch.
