JPEG images are usually corrupted by various undesirable compression artifacts resulted from block-wise coarse quantization on discrete cosine transform coefficients. In recent years, deep convolutional neural networks (CNNs) have made spectacular achievements in compression artifacts reduction. However, most deep CNNs are difficult to be implemented on mobile devices due to their large number of parameters and operations. In this letter, we propose a novel deep CNN called ESCNet for lightweight JPEG compression artifacts reduction, in which enhanced separable convolution (ESConv) is carefully designed to make full use of image multi-scale information for better dense pixel value predictions. Specifically, ESConv consists of a grouped multi-scale dual depth-wise convolution (GMDDConv) and a wide-activated dual point-wise convolution (WDPConv). GMDDConv is dedicated to efficiently extracting abundant image multi-scale spatial features, which will be sent to WDPConv for effective non-linear feature fusion. The experimental results on benchmark datasets show that compared with state-of-the-art methods, our ESCNet not only achieves better performance in both objective indices and subjective quality but also greatly reduces network parameters and operations.

中文翻译：

---

用于减少轻量级 JPEG 压缩伪影的增强型可分离卷积网络


JPEG 图像通常会因离散余弦变换系数的分块粗量化而产生的各种不良压缩伪影而受到损坏。近年来，深度卷积神经网络（CNN）在减少压缩伪影方面取得了令人瞩目的成就。然而，大多数深度 CNN 由于参数和操作数量较多，很难在移动设备上实现。在这封信中，我们提出了一种名为 ESCNet 的新型深度 CNN，用于减少轻量级 JPEG 压缩伪影，其中增强型可分离卷积（ESConv）经过精心设计，以充分利用图像多尺度信息来实现更好的密集像素值预测。具体来说，ESConv 由分组多尺度双深度卷积（GMDDConv）和宽激活双点卷积（WDPConv）组成。 GMDDConv致力于高效提取丰富的图像多尺度空间特征，将其发送到WDPConv进行有效的非线性特征融合。在基准数据集上的实验结果表明，与最先进的方法相比，我们的ESCNet不仅在客观指标和主观质量方面都取得了更好的性能，而且还大大减少了网络参数和操作。