Semantic Line Detection Using Mirror Attention and Comparative Ranking and Matching
This work addresses the problem of accurately detecting semantic lines in images for computer vision applications, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles semantic line detection by proposing a novel algorithm with three networks (D-Net, R-Net, M-Net) that use mirror attention and comparative ranking to extract and refine lines, resulting in significant outperformance over conventional detectors and successful application to dominant parallel lines and reflection symmetry axes.
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.