并行流域分割：基于 GPU 的层次化图像分割
Parallel Watershed Partitioning: GPU-Based Hierarchical Image Segmentation
AI总结：
本文提出三种 GPU 并行流域分割算法，通过迭代生成层次化瀑布区域，在 2D/3D 图像上实现高速处理，并可替代超像素用于语义分割预处理。
摘要：
许多图像处理应用依赖于将图像划分为像素“相似”的互不相交区域。流域变换和瀑布变换是成熟的数学形态学像素聚类技术。它们都与现代应用相关：在这些应用中，需要一次性判定成组像素，或者邻接信息具有重要作用。我们提出了三种面向 GPU 的新型并行分割算法。通过反复应用流域算法，我们生成瀑布结果，这些结果在输入图像上形成由分割区域组成的层次结构。我们的流域算法在二维和三维场景中均取得具有竞争力的执行时间，可在 1.4 秒内处理一幅 800 兆体素的图像。我们还展示了如何将这种完全确定性的图像分割用作基于机器学习的语义分割的预处理步骤。该方法取代了超像素算法的作用，并获得了相当的准确率和更快的训练时间。
英文摘要：
Many image processing applications rely on partitioning an image into disjoint regions whose pixels are 'similar.' The watershed and waterfall transforms are established mathematical morphology pixel clustering techniques. They are both relevant to modern applications where groups of pixels are to be decided upon in one go, or where adjacency information is relevant. We introduce three new parallel partitioning algorithms for GPUs. By repeatedly applying watershed algorithms, we produce waterfall results which form a hierarchy of partition regions over an input image. Our watershed algorithms attain competitive execution times in both 2D and 3D, processing an 800 megavoxel image in less than 1.4 sec. We also show how to use this fully deterministic image partitioning as a pre-processing step to machine learning based semantic segmentation. This replaces the role of superpixel algorithms, and results in comparable accuracy and faster training times.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
