Semantic Line Combination Detector

Jinwon Ko, Dongkwon Jin, Chang-Su Kim
2/9/2026

No official code found. Best implementation: Jinwon-Ko/SLCD (27 stars, Apache-2.0, PyTorch, last commit 2025-10-29).

Abstract

A novel algorithm, called semantic line combination detector (SLCD), to find an optimal combination of semantic lines is proposed in this paper. It processes all lines in each line combination at once to assess the overall harmony of the lines. First, we generate various line combinations from reliable lines. Second, we estimate the score of each line combination and determine the best one. Experimental results demonstrate that the proposed SLCD outperforms existing semantic line detectors on various datasets. More-over, it is shown that SLCD can be applied effectively to three vision tasks of vanishing point detection, symmetry axis detection, and composition-based image retrieval. Our codes are available at https://github.com/Jinwon-Ko/SLCD.

View on arXivView PDF

Code Implementations(1)

Jinwon-Ko/SLCDCommunity100%
PyTorchApache-2.0

Semantic Line Combination Detector, CVPR 2024.

272PythonMar 4, 202411 months agoApache-2.0
line-detectionpytorchsemantic-line-detection

Similar Papers

Aligned Anchor Groups Guided Line Segment Detector

80% match1 repo42025

TGGLinesPlus: A robust topological graph-guided computer vision algorithm for line detection from images

79% match1 repo52024

U3M: Unbiased Multiscale Modal Fusion Model for Multimodal Semantic Segmentation

78% match1 repo102024

Convex Relaxation for Robust Vanishing Point Estimation in Manhattan World

77% match1 repo1502026

DT-LSD: Deformable Transformer-based Line Segment Detection

77% match1 repo452024

ET-Former: Efficient Triplane Deformable Attention for 3D Semantic Scene Completion From Monocular Camera

77% match2024

Cite this paper

@article{ko2026semantic,
  title  = {Semantic Line Combination Detector},
  author = {Jinwon Ko and Dongkwon Jin and Chang-Su Kim},
  year   = {2026},
  eprint = {2404.18399},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/pdf/2404.18399},
  journal = {CVPR 2024 2024}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2404.18399.svg)](https://codeofpaper.com/paper/2404.18399)

Discussion