用生成模型做边缘检测，小样本也能出清晰结果。
EasyControlEdge: A Foundation-Model Fine-Tuning for Edge Detection
- 用图像生成模型的先验知识，结合像素级损失提升边缘精度。
- 在有限数据下仍能保持高清晰度，比现有方法更优。
- 适合资源受限场景，如医疗或遥感图像边缘提取。
我们提出 EasyControlEdge，将图像生成基础模型适配用于边缘检测。在真实场景中（如平面图墙体、卫星影像道路/建筑、医学器官边界），边缘清晰度与数据效率至关重要，但仅用少量训练样本生成清晰原始边缘图仍具挑战。尽管图像生成基础模型在众多下游任务中表现良好，其预训练先验在小样本迁移中的潜力以及迭代优化对高频细节的保留能力，在边缘检测中尚未被充分挖掘。为利用这些优势实现清晰且数据高效的边缘检测，我们提出一种面向边缘检测的专用微调方法。通过引入面向边缘的损失函数，提升模型在像素空间的表达能力；推理时采用无条件动态引导机制，仅通过调节引导系数即可控制边缘密度。在 BSDS500、NYUDv2、BIPED 与 CubiCasa 上的实验表明，该方法相比当前最优方法持续取得提升，尤其在无需后处理的清晰度评估和小样本条件下表现突出。
原文摘要 · Abstract (English)
We propose EasyControlEdge, adapting an image-generation foundation model to edge detection. In real-world edge detection (e.g., floor-plan walls, satellite roads/buildings, and medical organ boundaries), crispness and data efficiency are crucial, yet producing crisp raw edge maps with limited training samples remains challenging. Although image-generation foundation models perform well on many downstream tasks, their pretrained priors for data-efficient transfer and iterative refinement for high-frequency detail preservation remain underexploited for edge detection. To enable crisp and data-efficient edge detection using these capabilities, we introduce an edge-specialized adaptation of image-generation foundation models. To better specialize the foundation model for edge detection, we incorporate an edge-oriented objective with an efficient pixel-space loss. At inference, we introduce guidance based on unconditional dynamics, enabling a single model to control the edge density through a guidance scale. Experiments on BSDS500, NYUDv2, BIPED, and CubiCasa compare against state-of-the-art methods and show consistent gains, particularly under no-post-processing crispness evaluation and with limited training data.
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。