论文标题
连接场：在低SNR处提取边界结构
Field of Junctions: Extracting Boundary Structure at Low SNR
论文作者
论文摘要
我们介绍了一个自下而上的模型，以同时在图像中找到许多边界元素，包括轮廓，角落和连接处。该模型使用包含M角和自由移动顶点的“广义M结”来解释每个小斑块中的边界形状。使用非凸优化对图像进行分析，以在每个位置合作找到M+2连接值，而新型正常器会实现空间一致性，从而在保持角落和交界处的同时降低曲率。由此产生的“连接场”同时是轮廓探测器，角/连接探测器以及区域外观的边界意识平滑。值得注意的是，其对轮廓，角落，连接和统一区域的统一分析使其能够在高噪声水平上取得成功，而其他用于分割和边界检测方法的方法失败了。
We introduce a bottom-up model for simultaneously finding many boundary elements in an image, including contours, corners and junctions. The model explains boundary shape in each small patch using a 'generalized M-junction' comprising M angles and a freely-moving vertex. Images are analyzed using non-convex optimization to cooperatively find M+2 junction values at every location, with spatial consistency being enforced by a novel regularizer that reduces curvature while preserving corners and junctions. The resulting 'field of junctions' is simultaneously a contour detector, corner/junction detector, and boundary-aware smoothing of regional appearance. Notably, its unified analysis of contours, corners, junctions and uniform regions allows it to succeed at high noise levels, where other methods for segmentation and boundary detection fail.
