arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.07796eess.IV
收藏

基于块回归卷积神经网络(CNN)的非均匀运动模糊估计

Estimation of non-uniform motion blur using a patch-based regression convolutional neural network (CNN)

Luis G. Varela, Laura E. Boucheron, Steven Sandoval, David Voelz, Abu Bucker Siddik

AI总结:

本研究提出一种回归CNN,在块级别预测非均匀运动模糊的角度和长度,通过交替块大小训练,在多种块大小下获得高决定系数,验证了该方法在模糊特征预测中的有效性。

摘要:

大气湍流的非均匀模糊可以在块级别上建模为线性运动模糊核的叠加。我们提出了一种回归卷积神经网络(CNN),用于预测不同大小块对应的线性运动模糊核的角度和长度。我们分析了网络在不同块大小下的鲁棒性,以及在模糊特征过渡区域的网络性能。在训练过程中交替使用不同块大小,我们发现对于长度预测,决定系数$R^2>0.78$,对于角度预测,$R^2>0.94$,覆盖一系列块大小。我们发现,在重叠两种模糊特征的区域,模糊预测随重叠变化而在两种特征之间过渡。这些结果验证了此类网络在块级别上预测非均匀模糊特征的有效性。

英文摘要:

The non-uniform blur of atmospheric turbulence can be modeled as a superposition of linear motion blur kernels at a patch level. We propose a regression convolutional neural network (CNN) to predict angle and length of a linear motion blur kernel for varying sized patches. We analyze the robustness of the network for different patch sizes and the performance of the network in regions where the characteristics of the blur are transitioning. Alternating patch sizes per epoch in training, we find coefficient of determination scores across a range of patch sizes of $R^2>0.78$ for length and $R^2>0.94$ for angle prediction. We find that blur predictions in regions overlapping two blur characteristics transition between the two characteristics as overlap changes. These results validate the use of such a network for prediction of non-uniform blur characteristics at a patch level.

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。

↑