We focus on a fundamental task of detecting meaningful line structures, a.k.a., semantic line, in natural scenes. Many previous methods regard this problem as a special case of object detection and adjust existing object detectors for semantic line detection. However, these methods neglect the inherent characteristics of lines, leading to sub-optimal performance. Lines enjoy much simpler geometric property than complex objects and thus can be compactly parameterized by a few arguments. In this paper, we incorporate the classical Hough transform technique into deeply learned representations and propose a one-shot end-to-end learning framework for line detection. By parameterizing lines with slopes and biases, we perform Hough transform to translate deep representations into the parametric domain, in which we perform line detection. Specifically, we aggregate features along candidate lines on the feature map plane and then assign the aggregated features to corresponding locations in the parametric domain. The problem of detecting semantic lines in the spatial domain is transformed into spotting individual points in the parametric domain, making the post-processing steps, i.e., non-maximal suppression, more efficient. Experimental results on our proposed dataset and another public dataset demonstrate the advantages of our method over previous state-of-the-art alternatives.

中文翻译：

---

用于语义线检测的Deep Hough变换。

我们专注于检测自然场景中有意义的线结构（又名语义线）的基本任务。许多以前的方法都将此问题视为对象检测的特殊情况，并调整现有对象检测器以进行语义线检测。但是，这些方法忽略了线路的固有特性，从而导致性能欠佳。线比复杂的对象具有更简单的几何特性，因此可以通过几个参数紧凑地进行参数化。在本文中，我们将经典的Hough变换技术结合到了深度学习的表示中，并提出了一种用于线检测的端到端单次学习框架。通过使用斜率和偏差对线进行参数化，我们执行霍夫变换以将深度表示转换为参数域，然后在其中进行线检测。具体来说，我们沿着要素地图平面上的候选线聚合要素，然后将聚合的要素分配给参数域中的相应位置。在空间域中检测语义线的问题被转换为在参数域中发现单个点，从而使后处理步骤（即非最大抑制）更加有效。在我们提出的数据集和另一个公共数据集上的实验结果证明了我们的方法相对于以前的最新技术的优势。使后处理步骤（即非最大抑制）更加有效。在我们提出的数据集和另一个公共数据集上的实验结果证明了我们的方法相对于以前的最新技术的优势。使后处理步骤（即非最大抑制）更加有效。在我们提出的数据集和另一个公共数据集上的实验结果证明了我们的方法相对于以前的最新技术的优势。