Line segments are ubiquitous in our human-made world and are increasingly used in vision
tasks. They are complementary to feature points thanks to their spatial extent and the …

In contrast to sparse keypoints, a handful of line segments can concisely encode the high-
level scene layout, as they often delineate the main structural elements. In addition to …

Compared to feature point detection and description, detecting and matching line segments
offer additional challenges. Yet, line features represent a promising complement to points for …

Previous deep learning-based line segment detection (LSD) suffers from the immense
model size and high computational cost for line prediction. This constrains them from real …

An image line segment is a fundamental low-level visual feature that delineates straight,
slender, and uninterrupted portionsof objects and scenarios within images. Detection and …

Visual Simultaneous Localization and Mapping (VSLAM), which serves as the primary
technique for locating autonomous vehicles, has gained tremendous development over the …

This article presents Holistically-Attracted Wireframe Parsing (HAWP), a method for
geometric analysis of 2D images containing wireframes formed by line segments and …

We present a one-stage Fully Convolutional Line P arsing network (F-Clip) that detects line
segments from images. The proposed network is very simple and flexible with variations that …

Abstract Structure-from-Motion (SfM) has become a ubiquitous tool for camera calibration
and scene reconstruction with many downstream applications in computer vision and …

We present the novel Efficient Line Segment Detector and Descriptor (ELSD) to
simultaneously detect line segments and extract their descriptors in an image. Unlike the …