论文标题
LGNN：上下文感知线段检测器
LGNN: A Context-aware Line Segment Detector
论文作者
论文摘要
我们提出了一种新型的实时线段检测方案，称为线图神经网络（LGNN）。现有方法需要计算昂贵的验证或后处理步骤。我们的LGNN采用深度卷积神经网络（DCNN）直接提出线段，并使用图形神经网络（GNN）模块来推理其连接性。具体而言，LGNN为每个行段中利用了新的四倍表示，其中GNN模块将预测的候选者作为顶点构成，并构造了一个稀疏的图形来强制实施结构上下文。与最新的ART相比，LGNN实现了几乎实时性能，而不会损害准确性。 LGNN进一步启用时间敏感的3D应用。当可以访问3D点云时，我们提出了一种多模式线段分类技术，用于稳健有效地提取环境的3D线框。
We present a novel real-time line segment detection scheme called Line Graph Neural Network (LGNN). Existing approaches require a computationally expensive verification or postprocessing step. Our LGNN employs a deep convolutional neural network (DCNN) for proposing line segment directly, with a graph neural network (GNN) module for reasoning their connectivities. Specifically, LGNN exploits a new quadruplet representation for each line segment where the GNN module takes the predicted candidates as vertexes and constructs a sparse graph to enforce structural context. Compared with the state-of-the-art, LGNN achieves near real-time performance without compromising accuracy. LGNN further enables time-sensitive 3D applications. When a 3D point cloud is accessible, we present a multi-modal line segment classification technique for extracting a 3D wireframe of the environment robustly and efficiently.
