用可变形Transformer提升线段检测速度与精度，超越传统CNN方法。
DT-LSD: Deformable Transformer-based Line Segment Detection
- 采用可变形Transformer设计，支持跨尺度交互，优化特征提取。
- 训练速度提升34倍，Wireframe数据集上sAP10达71.7，优于所有已有模型。
- 适合需要高效高精度线段检测的视觉任务，如场景理解与自动驾驶。
线段检测是计算机视觉中的基础低层任务，其性能提升将影响依赖它的高级方法。现有多数方法基于卷积神经网络（CNN），而基于变换器的方法应用受限。本文提出新型检测器DT-LSD，解决LETR模型缺陷。为加速训练，引入线段对比去噪（LCDN）技术，使训练速度提升34倍。实验表明，DT-LSD在速度和精度上均优于LETR，并在准确率上超过所有CNN基线模型：在Wireframe数据集上，sAP¹⁰达到71.7，sAP¹⁵达到73.9；在YorkUrban数据集上，分别达到33.2和35.1。
原文摘要 · Abstract (English)
Line segment detection is a fundamental low-level task in computer vision, and improvements in this task can impact more advanced methods that depend on it. Most new methods developed for line segment detection are based on Convolutional Neural Networks (CNNs). Our paper seeks to address challenges that prevent the wider adoption of transformer-based methods for line segment detection. More specifically, we introduce a new model called Deformable Transformer-based Line Segment Detection (DT-LSD) that supports cross-scale interactions and can be trained quickly. This work proposes a novel Deformable Transformer-based Line Segment Detector (DT-LSD) that addresses LETR's drawbacks. For faster training, we introduce Line Contrastive DeNoising (LCDN), a technique that stabilizes the one-to-one matching process and speeds up training by 34$\times$. We show that DT-LSD is faster and more accurate than its predecessor transformer-based model (LETR) and outperforms all CNN-based models in terms of accuracy. In the Wireframe dataset, DT-LSD achieves 71.7 for $sAP^{10}$ and 73.9 for $sAP^{15}$; while 33.2 for $sAP^{10}$ and 35.1 for $sAP^{15}$ in the YorkUrban dataset.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。