Abstract
Generating crisp, i.e., one-pixel-wide, edge maps remains one of the fundamental challenges in edge detection, affecting both traditional and learning-based methods. To obtain crisp edges, most existing approaches rely on two hand-crafted post-processing algorithms, Non-Maximum Suppression (NMS) and skeleton-based thinning, which are non-differentiable and hinder end-to-end optimization. Moreover, all existing crisp edge detection methods still depend on such post-processing to achieve satisfactory results. To address this limitation, we propose \MethodLPP, a lightweight, only $\sim$21K additional parameters, and plug-and-play matching-based supervision module that can be appended to any edge detection model for joint end-to-end learning of crisp edges. At each training iteration, \MethodLPP performs one-to-one matching between predicted and ground-truth edges based on spatial distance and confidence, ensuring consistency between training and testing protocols. Extensive experiments on four popular datasets demonstrate that integrating \MethodLPP substantially improves the performance of existing edge detection models. In particular, \MethodLPP increases the Average Crispness (AC) metric by up to 2--4$\times$ compared to baseline models. Under the crispness-emphasized evaluation (CEval), \MethodLPP further boosts baseline performance by up to 20--35\% in ODS and achieves similar gains in OIS and AP, achieving SOTA performance that matches or surpasses standard post-processing for the first time. Code is available at this https URL.
Abstract (translated)
生成清晰的边缘地图（即单像素宽）仍然是边缘检测中的一个基本挑战，影响着传统的和基于学习的方法。为了获取清晰的边缘，现有的大多数方法依赖于两种手工设计的后处理算法：非极大值抑制（NMS）和骨架细化。这些算法是非可微分的，阻碍了端到端优化过程。此外，所有现有的清晰边缘检测方法仍然需要这种后处理才能取得满意的结果。 为了克服这一限制，我们提出了\MethodLPP，这是一种轻量级的方法，大约只需要21K个附加参数，并且可以插入任何边缘检测模型中以进行联合的端到端学习，用于生成清晰的边缘。在每次训练迭代过程中，\MethodLPP 基于空间距离和置信度执行预测边缘与真实边缘之间的一对一匹配操作，确保了训练和测试协议之间的一致性。 我们在四个流行的数据集上进行了广泛的实验，结果表明将\MethodLPP 集成到现有的边缘检测模型中可以显著提高这些模型的性能。特别是在平均清晰度（AC）指标方面，与基线模型相比，\MethodLPP 可以提升2-4倍。在强调清晰度评估（CEval）下，\MethodLPP 还能将基线模型的表现提升最多达20%-35%在开放性数据集上，并且在开放性图像集合和平均精度方面也实现了相似的改进，这是首次达到了与标准后处理相匹配或超越其性能的标准。 代码可在以下链接获取：[提供的链接]。
URL
https://arxiv.org/abs/2602.20689
