arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.05892cs.CVcs.LGeess.IV
收藏

LGNN:一种上下文感知的线段检测器

LGNN: A Context-aware Line Segment Detector

ShanghaiTech University(上海科技大学);Shanghai Engineering Research Center of Intelligent Vision and Imaging, School of Information Science and Technology, ShanghaiTech University(上海科技大学信息科学与技术学院智能视觉与成像上海工程技术研究中心)

Quan Meng, Jiakai Zhang, Qiang Hu, Xuming He, Jingyi Yu

摘要:

我们提出了一种新的实时线段检测方案称为线图神经网络(LGNN)。现有的方法需要计算上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,图神经网络(GNN)模块推理其连通性。具体来说,LGNN为每个线段采用了一种新的四元组表示,其中GNN模块将预测的候选项作为顶点,并构建一个稀疏图来执行结构上下文。与现有技术相比,LGNN在不影响精度的情况下实现了接近实时的性能。LGNN进一步实现了对时间敏感的3D应用。当一个三维点云是可访问的,我们提出了一个多模态线段分类技术提取的三维线框的环境鲁棒性和有效性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑