论文标题
用点形式检测3D对象检测
3D Object Detection with Pointformer
论文作者
论文摘要
由于3D点云数据的不规则性，从点云中检测3D对象检测的功能学习非常具有挑战性。在本文中，我们提出了PointFormer，这是一种为3D点云设计的变压器骨干，以有效地学习功能。具体而言，使用本地变压器模块来模拟局部区域中点之间的交互作用，该模块在对象级别学习上下文依赖于上下文的区域特征。全球变压器旨在在场景级别学习上下文感知的表示。为了进一步捕获多尺度表示之间的依赖关系，我们建议本地 - 全球变压器将本地特征与高分辨率的全局特征集成在一起。此外，我们还引入了一个有效的坐标改进模块，以将采样的点更接近对象质心移动，从而改善对象建议的产生。我们将PointFormer用作最先进的对象检测模型的骨干，并在室内和室外数据集的原始模型中显示出显着改进。
Feature learning for 3D object detection from point clouds is very challenging due to the irregularity of 3D point cloud data. In this paper, we propose Pointformer, a Transformer backbone designed for 3D point clouds to learn features effectively. Specifically, a Local Transformer module is employed to model interactions among points in a local region, which learns context-dependent region features at an object level. A Global Transformer is designed to learn context-aware representations at the scene level. To further capture the dependencies among multi-scale representations, we propose Local-Global Transformer to integrate local features with global features from higher resolution. In addition, we introduce an efficient coordinate refinement module to shift down-sampled points closer to object centroids, which improves object proposal generation. We use Pointformer as the backbone for state-of-the-art object detection models and demonstrate significant improvements over original models on both indoor and outdoor datasets.
