论文标题
隐式Euler ode网络用于单位图
Implicit Euler ODE Networks for Single-Image Dehazing
论文作者
论文摘要
深度卷积神经网络（CNN）已应用于图像飞机任务，其中残留网络（RESNET）通常被用作避免消失的梯度问题的基本组件。最近，许多作品表明，可以将重新系统视为普通微分方程（ODE）的显式欧拉前近似。在本文中，我们将明确的正向近似扩展到隐式向后的对应物，该近似可以通过递归神经网络（名为IM-Block）实现。鉴于此，我们为单个图像去悬式问题提出了一个有效的端到端多级隐式网络（MI-NET）。此外，采用了多级融合（MLF）机制和残留的通道注意块（RCA-Block）来提高我们的网络性能。几个Dhazing基准数据集的实验表明，我们的方法的表现优于现有方法，并实现了最先进的性能。
Deep convolutional neural networks (CNN) have been applied for image dehazing tasks, where the residual network (ResNet) is often adopted as the basic component to avoid the vanishing gradient problem. Recently, many works indicate that the ResNet can be considered as the explicit Euler forward approximation of an ordinary differential equation (ODE). In this paper, we extend the explicit forward approximation to the implicit backward counterpart, which can be realized via a recursive neural network, named IM-block. Given that, we propose an efficient end-to-end multi-level implicit network (MI-Net) for the single image dehazing problem. Moreover, multi-level fusing (MLF) mechanism and residual channel attention block (RCA-block) are adopted to boost performance of our network. Experiments on several dehazing benchmark datasets demonstrate that our method outperforms existing methods and achieves the state-of-the-art performance.
