Semantic Line Detection Using Mirror Attention and Comparative Ranking and Matching

TL;DR

This paper introduces a novel semantic line detection algorithm utilizing mirror attention and comparative ranking/matching networks, outperforming existing methods and effectively detecting dominant parallel lines and reflection symmetry axes.

Contribution

The paper presents a new detection network with mirror attention and pairwise comparison networks for improved semantic line detection.

Findings

Outperforms conventional semantic line detectors significantly

Successfully detects dominant parallel lines

Effectively identifies reflection symmetry axes

Abstract

A novel algorithm to detect semantic lines is proposed in this paper. We develop three networks: detection network with mirror attention (D-Net) and comparative ranking and matching networks (R-Net and M-Net). D-Net extracts semantic lines by exploiting rich contextual information. To this end, we design the mirror attention module. Then, through pairwise comparisons of extracted semantic lines, we iteratively select the most semantic line and remove redundant ones overlapping with the selected one. For the pairwise comparisons, we develop R-Net and M-Net in the Siamese architecture. Experiments demonstrate that the proposed algorithm outperforms the conventional semantic line detector significantly. Moreover, we apply the proposed algorithm to detect two important kinds of semantic lines successfully: dominant parallel lines and reflection symmetry axes. Our codes are available at https://github.com/dongkwonjin/Semantic-Line-DRM.