论文标题
MSDU-NET：多尺度扩张的U-NET用于模糊检测
MSDU-net: A Multi-Scale Dilated U-net for Blur Detection
论文作者
论文摘要
模糊检测是图像模糊和清晰的区域的分离，这是计算机视觉中的一项重要且具有挑战性的任务。在这项工作中，我们将模糊检测视为图像分割问题。受U-NET体系结构用于图像分割的成功的启发，我们设计了一个基于U-NET的多尺度扩张卷积神经网络，我们称之为MSDU-NET。 MSDU-NET使用一组具有扩张卷积的多尺度特征提取器，以不同的尺度提取纹理信息。 MSDU-NET的U形架构融合了不同规模的纹理功能，并生成语义功能，使我们能够在模糊检测任务上获得更好的结果。我们表明，使用MSDU-NET，我们能够在两个公开可用的基准上胜过其他最先进的模糊检测方法。
Blur detection is the separation of blurred and clear regions of an image, which is an important and challenging task in computer vision. In this work, we regard blur detection as an image segmentation problem. Inspired by the success of the U-net architecture for image segmentation, we design a Multi-Scale Dilated convolutional neural network based on U-net, which we call MSDU-net. The MSDU-net uses a group of multi-scale feature extractors with dilated convolutions to extract texture information at different scales. The U-shape architecture of the MSDU-net fuses the different-scale texture features and generates a semantic feature which allows us to achieve better results on the blur detection task. We show that using the MSDU-net we are able to outperform other state of the art blur detection methods on two publicly available benchmarks.
