Deep convolutional neural networks have achieved great progress in image denoising tasks. However, their complicated architectures and heavy computational cost hinder their deployments on mobile devices. Some recent efforts in designing lightweight denoising networks focus on reducing either FLOPs (floating-point operations) or the number of parameters. However, these metrics are not directly correlated with the on-device latency. In this paper, we identify the real bottlenecks that affect the CNN-based models' run-time performance on mobile devices: memory access cost and NPU-incompatible operations, and build the model based on these. To further improve the denoising performance, the mobile-friendly attention module MFA and the model reparameterization module RepConv are proposed, which enjoy both low latency and excellent denoising performance. To this end, we propose a mobile-friendly denoising network, namely MFDNet. The experiments show that MFDNet achieves state-of-the-art performance on real-world denoising benchmarks SIDD and DND under real-time latency on mobile devices. The code and pre-trained models will be released.

翻译：深度卷积神经网络在图像去噪任务中取得了显著进展。然而，其复杂的架构和较高的计算成本阻碍了在移动设备上的部署。近期一些轻量级去噪网络的设计工作侧重于减少FLOPs（浮点运算次数）或参数量，但这些指标与设备端延迟并无直接关联。本文识别了影响基于CNN模型在移动设备上运行时性能的真正瓶颈——内存访问成本及不兼容NPU的操作——并据此构建模型。为进一步提升去噪性能，我们提出了移动端友好的注意力模块MFA和模型重参数化模块RepConv，二者兼具低延迟和优异的去噪性能。最终，我们构建了移动端友好去噪网络MFDNet。实验表明，MFDNet在真实世界去噪基准SIDD和DND上，以移动设备实时延迟取得了最先进的性能。相关代码与预训练模型将予以公开。