PPGNet: Learning Point-Pair Graph for Line Segment Detection
This work addresses the problem of structured line detection for computer vision applications, offering a novel graph-based approach that improves over existing methods, though it appears incremental in its specific domain.
The paper tackles line segment detection in man-made environments by proposing a graph-based representation for junctions and segments, and introduces PPGNet, a CNN that directly infers this graph from images, achieving satisfactory performance on benchmarks like York Urban and Wireframe datasets.
In this paper, we present a novel framework to detect line segments in man-made environments. Specifically, we propose to describe junctions, line segments and relationships between them with a simple graph, which is more structured and informative than end-point representation used in existing line segment detection methods. In order to extract a line segment graph from an image, we further introduce the PPGNet, a convolutional neural network that directly infers a graph from an image. We evaluate our method on published benchmarks including York Urban and Wireframe datasets. The results demonstrate that our method achieves satisfactory performance and generalizes well on all the benchmarks. The source code of our work is available at \url{https://github.com/svip-lab/PPGNet}.