论文标题
通过学习3D对象检测来改善点云语义细分
Improving Point Cloud Semantic Segmentation by Learning 3D Object Detection
论文作者
论文摘要
点云语义分割在自主驾驶中起着至关重要的作用，提供有关可驱动表面和附近物体的重要信息，这些信息可以帮助更高级别的任务，例如路径计划和避免碰撞。虽然当前的3D语义分割网络专注于表现出色的类别的卷积体系结构，但它们显示出具有相似几何特征的代表性不足类的性能下降。我们提出了一个新颖的检测意识到3D语义分割（DASS）框架，该框架明确利用了辅助3D对象检测任务的本地化特征。通过使用多任务培训，指导网络的共享特征表示形式，以了解每个类检测功能，以帮助解决几何相似类的差异化。我们还提供了一条使用DASS为现有2阶段检测器生成高召回建议的管道，并证明可增加的监督信号可用于提高3D方向估计功能。 Semantickitti和Kitti对象数据集的广泛实验表明，DASS可以改善几何相似类的3D语义分割结果，最高37.8％，同时保持高精度鸟类视图（BEV）检测结果。
Point cloud semantic segmentation plays an essential role in autonomous driving, providing vital information about drivable surfaces and nearby objects that can aid higher level tasks such as path planning and collision avoidance. While current 3D semantic segmentation networks focus on convolutional architectures that perform great for well represented classes, they show a significant drop in performance for underrepresented classes that share similar geometric features. We propose a novel Detection Aware 3D Semantic Segmentation (DASS) framework that explicitly leverages localization features from an auxiliary 3D object detection task. By utilizing multitask training, the shared feature representation of the network is guided to be aware of per class detection features that aid tackling the differentiation of geometrically similar classes. We additionally provide a pipeline that uses DASS to generate high recall proposals for existing 2-stage detectors and demonstrate that the added supervisory signal can be used to improve 3D orientation estimation capabilities. Extensive experiments on both the SemanticKITTI and KITTI object datasets show that DASS can improve 3D semantic segmentation results of geometrically similar classes up to 37.8% IoU in image FOV while maintaining high precision bird's-eye view (BEV) detection results.
