论文标题
AMVNET：基于断言的多视图融合网络，用于激光雷达语义分段
AMVNet: Assertion-based Multi-View Fusion Network for LiDAR Semantic Segmentation
论文作者
论文摘要
在本文中，我们提出了一种基于断言的多视图融合网络（AMVNET），用于LIDAR语义分割，该网络分割，该网络使用晚融合汇总了基于晚融合的单个投影网络的语义特征。给定的基于不同投影的网络的类得分，我们对分数分歧进行断言引导的点采样，并将每个采样点的一组点级特征传递到一个简单的点头，以完善预测。这种模块化和层次结构的晚期融合方法提供了具有两个独立网络，其中两个独立的网络和轻质网络的次要开销。这种方法对于机器人系统是可取的，例如自动驾驶汽车，计算和内存资源通常受到限制。广泛的实验表明，AMVNET达到最新的实验会导致Semantickitti和Nuscenes基准数据集，并且我们的方法优于将基于投影基于投影的网络的类别分数组合的基线方法。
In this paper, we present an Assertion-based Multi-View Fusion network (AMVNet) for LiDAR semantic segmentation which aggregates the semantic features of individual projection-based networks using late fusion. Given class scores from different projection-based networks, we perform assertion-guided point sampling on score disagreements and pass a set of point-level features for each sampled point to a simple point head which refines the predictions. This modular-and-hierarchical late fusion approach provides the flexibility of having two independent networks with a minor overhead from a light-weight network. Such approaches are desirable for robotic systems, e.g. autonomous vehicles, for which the computational and memory resources are often limited. Extensive experiments show that AMVNet achieves state-of-the-art results in both the SemanticKITTI and nuScenes benchmark datasets and that our approach outperforms the baseline method of combining the class scores of the projection-based networks.
