论文标题
快速图像通过固定点和梯度下降加速度反向过滤器
Fast image reverse filters through fixed point and gradient descent acceleration
论文作者
论文摘要
在本文中，我们研究了反向图像过滤的问题。图像过滤器表示为黑框的G（。），当提供输入X时会产生观察B = G（X）。问题是要从黑匣子滤波器g（。）和观察b估算原始输入信号x。我们从两个观点，固定点迭代和梯度下降研究并重新开发最新方法。我们还探索了两种迭代类型的加速技术的应用。通过广泛的实验和比较，我们表明了固定点迭代和梯度下降的加速方法有助于加快最新方法的收敛性。
In this paper, we study the problem of reverse image filtering. An image filter denoted g(.), which is available as a black box, produces an observation b = g(x) when provided with an input x. The problem is to estimate the original input signal x from the black box filter g(.) and the observation b. We study and re-develop state-of-the-art methods from two points of view, fixed point iteration and gradient descent. We also explore the application of acceleration techniques for the two types of iterations. Through extensive experiments and comparison, we show that acceleration methods for both fixed point iteration and gradient descent help to speed up the convergence of state-of-the-art methods.
