Semantic Line Detection Using Mirror Attention and Comparative Ranking and Matching
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.
Code (1)
Tasks
Line DetectionSimilar Papers 제목 키워드 기반
Symmetry-Aware Transformer-based Mirror Detection
Mirror detection aims to identify the mirror regions in the given input image. Existing works mainly focus on integrating the semantic features and structural features to mine specific relations between mirror and non-mi…
DecoderMirror DetectionMirror-Yolo: A Novel Attention Focus, Instance Segmentation and Mirror Detection Model
Mirrors can degrade the performance of computer vision models, but research into detecting them is in the preliminary phase. YOLOv4 achieves phenomenal results in terms of object detection accuracy and speed, but it stil…
Instance SegmentationMirror Detectionobject-detectionObject Detection+1Effective Video Mirror Detection with Inconsistent Motion Cues
Image-based mirror detection has recently undergone rapid research due to its significance in applications such as robotic navigation semantic segmentation and scene reconstruction. Recently VMD-Net was proposed as t…
Edge DetectionMirror DetectionOptical Flow EstimationSemantic SegmentationLearning Semantic Associations for Mirror Detection
Mirrors generally lack a consistent visual appearance, making mirror detection very challenging. Although recent works that are based on exploiting contextual contrasts and corresponding relations have achieved good …
Image SegmentationMirror DetectionEfficient Mirror Detection via Multi-level Heterogeneous Learning
We present HetNet (Multi-level \textbf{Het}erogeneous \textbf{Net}work), a highly efficient mirror detection network. Current mirror detection methods focus more on performance than efficiency, limiting the real-time app…
Image SegmentationMirror Detection