arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1704.08992cs.CV
收藏

一种多尺度深度特征与手工特征相结合的散焦估计方法

A Unified Approach of Multi-scale Deep and Hand-crafted Features for Defocus Estimation

KAIST(韩国科学技术院);Tencent YouTu Lab(腾讯优图实验室)

Jinsun Park, Yu-Wing Tai, Donghyeon Cho, In So Kweon

摘要:

在本文中,我们介绍了强大的和协同的手工制作的功能和一个简单但有效的深度功能,从卷积神经网络(CNN)架构的散焦估计。本文系统地分析了不同特征的有效性,并展示了当它们连接在一起时,每个特征如何弥补其他特征的弱点。对于完整的散焦图估计,我们稀疏地提取强边缘上的图像块,之后我们使用它们进行深度和手工特征提取。为了降低块尺度依赖程度,我们还提出了一种多尺度块提取策略。稀疏散焦图是使用神经网络分类器生成的,然后是概率联合双边滤波器。最终散焦图是在来自边缘保留滤波输入图像的指导下从稀疏散焦图获得的。实验结果表明,我们的算法是优于国家的最先进的算法在离焦估计。我们的工作可用于应用程序,如分割,模糊放大,全聚焦图像生成,和3-D估计。

英文摘要:

In this paper, we introduce robust and synergetic hand-crafted features and a simple but efficient deep feature from a convolutional neural network (CNN) architecture for defocus estimation. This paper systematically analyzes the effectiveness of different features, and shows how each feature can compensate for the weaknesses of other features when they are concatenated. For a full defocus map estimation, we extract image patches on strong edges sparsely, after which we use them for deep and hand-crafted feature extraction. In order to reduce the degree of patch-scale dependency, we also propose a multi-scale patch extraction strategy. A sparse defocus map is generated using a neural network classifier followed by a probability-joint bilateral filter. The final defocus map is obtained from the sparse defocus map with guidance from an edge-preserving filtered input image. Experimental results show that our algorithm is superior to state-of-the-art algorithms in terms of defocus estimation. Our work can be used for applications such as segmentation, blur magnification, all-in-focus image generation, and 3-D estimation.

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。

↑