This paper focuses on the limitations of current over-parameterized shadow removal models. We present a novel lightweight deep neural network that processes shadow images in the LAB color space. The proposed network termed "LAB-Net", is motivated by the following three observations: First, the LAB color space can well separate the luminance information and color properties. Second, sequentially-stacked convolutional layers fail to take full use of features from different receptive fields. Third, non-shadow regions are important prior knowledge to diminish the drastic color difference between shadow and non-shadow regions. Consequently, we design our LAB-Net by involving a two-branch structure: L and AB branches. Thus the shadow-related luminance information can well be processed in the L branch, while the color property is well retained in the AB branch. In addition, each branch is composed of several Basic Blocks, local spatial attention modules (LSA), and convolutional filters. Each Basic Block consists of multiple parallelized dilated convolutions of divergent dilation rates to receive different receptive fields that are operated with distinct network widths to save model parameters and computational costs. Then, an enhanced channel attention module (ECA) is constructed to aggregate features from different receptive fields for better shadow removal. Finally, the LSA modules are further developed to fully use the prior information in non-shadow regions to cleanse the shadow regions. We perform extensive experiments on the both ISTD and SRD datasets. Experimental results show that our LAB-Net well outperforms state-of-the-art methods. Also, our model's parameters and computational costs are reduced by several orders of magnitude. Our code is available at https://github.com/ngrxmu/LAB-Net.
翻译:本文侧重于当前超参数化的阴影清除模型的局限性。 我们展示了一个新颖的轻量深神经网络, 处理LAB 色彩空间中的阴影图像。 拟议的网络名为“ LAB- Net ”, 受到以下三种观察的驱动: 首先, LAB 色彩空间可以将光亮信息和颜色属性完全分离。 其次, 依次排列的共振层不能充分利用不同接收域的特征。 第三, 非阴影区域是重要先知, 以缩小阴影区域和非阴影区域之间的巨大颜色差异。 因此, 我们设计我们的LAB- 网络网络网络网络网络网, 包括两个分支的光亮度参数结构: L和 AB 分支。 因此, 与阴影相关的亮度信息可以在L 分支中处理, 而颜色属性则保留在 AB 分支中。 此外, 每个分支由几个基本块、 地方空间关注模块(LSA) 和革命过滤器组成。 每个基本屏蔽区由多个平行的变相变形变形变形模型组成, 接收不同的接收不同的接受不同的接受不同的接收域域, 在不同的网络宽度上运行不同的网络宽度, 不同的网络的宽宽范围,, 到不同的网络的宽度, 从不同的网络, 和AIS变色变色变色模型的计算, 的计算成本, 以不同的计算成本, 以前的模型为不同的模型的模型的模型的模型的计算成本, 以不同的计算成本, 以不同的计算成本为不同的计算成本为不同的模型到我们的模型到前的模型,, 的模型到之前的模型, 我们的系统的模型的模型的模型的模型的模型的变变形变形变色域, 的变变变式的变式模型的变式模型的变式的变的变的变的变的变的变的变的变式,,,, 的变式模型的变的变的变式模型的变式模型的变式的变式的变换的变的变换的变换的变的变的变的变的变换的变的变的变的变的变的变的变的变的变的变的变的变的变的变的变的变的变的变的变式, 和变的变的变的变的变