论文标题
REAL3D-AUG：通过放置带有遮挡处理的真实对象进行3D检测和分段来增加点云
Real3D-Aug: Point Cloud Augmentation by Placing Real Objects with Occlusion Handling for 3D Detection and Segmentation
论文作者
论文摘要
使用3D激光点云数据的对象检测和语义分割需要昂贵的注释。我们提出了一种数据增强方法，该方法多次利用已经注释的数据。我们提出了一个重用真实数据的增强框架，自动在场景中找到合适的位置要增加，并明确处理遮挡。由于使用真实数据，新插入的物体在增强中的扫描点维持了激光雷达的物理特征，例如强度和射线表。该管道证明在训练3D对象检测和语义分段的最佳模型中具有竞争力。新的增强为稀有和必不可少的类别提供了显着的性能增长，尤其是Kitti对象检测中“硬”行人级的平均精度增长率为6.65％，或者2.14在Semantickitti细分挑战中，IOU在艺术状态下获得了IOU。
Object detection and semantic segmentation with the 3D lidar point cloud data require expensive annotation. We propose a data augmentation method that takes advantage of already annotated data multiple times. We propose an augmentation framework that reuses real data, automatically finds suitable placements in the scene to be augmented, and handles occlusions explicitly. Due to the usage of the real data, the scan points of newly inserted objects in augmentation sustain the physical characteristics of the lidar, such as intensity and raydrop. The pipeline proves competitive in training top-performing models for 3D object detection and semantic segmentation. The new augmentation provides a significant performance gain in rare and essential classes, notably 6.65% average precision gain for "Hard" pedestrian class in KITTI object detection or 2.14 mean IoU gain in the SemanticKITTI segmentation challenge over the state of the art.
