TP-LSD: Tri-Points Based Line Segment Detector

TL;DR

TP-LSD introduces a real-time deep learning model for line segment detection using tri-points representation, enabling end-to-end prediction and surpassing previous methods in speed and accuracy.

Contribution

The paper presents a novel tri-points based representation and a unified deep model for real-time line segment detection, simplifying the process and improving efficiency.

Findings

Achieves up to 78 FPS on 320x320 images.

Demonstrates competitive accuracy on Wireframe and YorkUrban datasets.

Introduces a new evaluation metric for line detection.

Abstract

This paper proposes a novel deep convolutional model, Tri-Points Based Line Segment Detector (TP-LSD), to detect line segments in an image at real-time speed. The previous related methods typically use the two-step strategy, relying on either heuristic post-process or extra classifier. To realize one-step detection with a faster and more compact model, we introduce the tri-points representation, converting the line segment detection to the end-to-end prediction of a root-point and two endpoints for each line segment. TP-LSD has two branches: tri-points extraction branch and line segmentation branch. The former predicts the heat map of root-points and the two displacement maps of endpoints. The latter segments the pixels on straight lines out from background. Moreover, the line segmentation map is reused in the first branch as structural prior. We propose an additional novel evaluation metric and evaluate our method on Wireframe and YorkUrban datasets, demonstrating not only the competitive accuracy compared to the most recent methods, but also the real-time run speed up to 78 FPS with the $320\times 320$ input.