Deep convolutional neural networks (CNNs) depend on feedforward and feedback ways to obtain good performance in image denoising. However, how to obtain effective structural information via CNNs to efficiently represent given noisy images is key for complex scenes. In this paper, we propose a cross Transformer denoising CNN (CTNet) with a serial block (SB), a parallel block (PB), and a residual block (RB) to obtain clean images for complex scenes. A SB uses an enhanced residual architecture to deeply search structural information for image denoising. To avoid loss of key information, PB uses three heterogeneous networks to implement multiple interactions of multi-level features to broadly search for extra information for improving the adaptability of an obtained denoiser for complex scenes. Also, to improve denoising performance, Transformer mechanisms are embedded into the SB and PB to extract complementary salient features for effectively removing noise in terms of pixel relations. Finally, a RB is applied to acquire clean images. Experiments illustrate that our CTNet is superior to some popular denoising methods in terms of real and synthetic image denoising. It is suitable to mobile digital devices, i.e., phones. Codes can be obtained at https://github.com/hellloxiaotian/CTNet.

翻译：深度卷积神经网络（CNNs）依赖前馈和反馈机制在图像去噪中取得良好性能。然而，如何通过CNNs获取有效的结构信息以高效表示给定噪声图像，是复杂场景下的关键问题。本文提出了一种交叉Transformer去噪CNN（CTNet），通过串行块（SB）、并行块（PB）和残差块（RB）获取复杂场景下的清晰图像。SB采用增强残差架构深度挖掘图像去噪的结构信息。为避免关键信息丢失，PB利用三个异构网络实现多级特征的多次交互，广泛搜索额外信息以提升所得去噪器对复杂场景的适应性。同时，为提升去噪性能，将Transformer机制嵌入SB和PB中，通过像素关系提取互补显著性特征以有效去除噪声。最后，采用RB获取清晰图像。实验表明，在真实和合成图像去噪方面，我们的CTNet优于多种主流去噪方法，适用于手机等移动数字设备。代码可访问https://github.com/hellloxiaotian/CTNet获取。