LGNN: a Context-aware Line Segment Detector

08/13/2020
by   Quan Meng, et al.
13

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.

READ FULL TEXT

page 1

page 5

page 7

page 8

research
03/02/2020

Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud

In this paper, we propose a graph neural network to detect objects from ...
research
05/09/2019

PPGNet: Learning Point-Pair Graph for Line Segment Detection

In this paper, we present a novel framework to detect line segments in m...
research
06/01/2021

Towards Real-time and Light-weight Line Segment Detection

Previous deep learning-based line segment detection (LSD) suffer from th...
research
09/11/2020

TP-LSD: Tri-Points Based Line Segment Detector

This paper proposes a novel deep convolutional model, Tri-Points Based L...
research
03/07/2023

Parsing Line Segments of Floor Plan Images Using Graph Neural Networks

In this paper, we present a GNN-based Line Segment Parser (GLSP), which ...
research
03/31/2020

Scene Context Based Semantic Segmentation for 3D LiDAR Data in Dynamic Scene

We propose a graph neural network(GNN) based method to incorporate scene...
research
12/05/2018

Learning Attraction Field Representation for Robust Line Segment Detection

This paper presents a region-partition based attraction field dual repre...

Please sign up or login with your details

Forgot password? Click here to reset