Low level image restoration is an integral component of modern artificial intelligence (AI) driven camera pipelines. Most of these frameworks are based on deep neural networks which present a massive computational overhead on resource constrained platform like a mobile phone. In this paper, we propose several lightweight low-level modules which can be used to create a computationally low cost variant of a given baseline model. Recent works for efficient neural networks design have mainly focused on classification. However, low-level image processing falls under the ‘image-to-image’ translation genre which requires some additional computational modules not present in classification. This paper seeks to bridge this gap by designing generic efficient modules which can replace essential components used in contemporary deep learning based image restoration networks. We also present and analyse our results highlighting the drawbacks of applying depthwise separable convolutional kernel (a popular method for efficient classification network) for sub-pixel convolution based upsampling (a popular upsampling strategy for low-level vision applications). This shows that concepts from domain of classification cannot always be seamlessly integrated into ‘image-to-image’ translation tasks. We extensively validate our findings on three popular tasks of image inpainting, denoising and super-resolution. Our results show that proposed networks consistently output visually similar reconstructions compared to full capacity baselines with significant reduction of parameters, memory footprint and execution speeds on contemporary mobile devices.

中文翻译：

---

用于基于深度学习的高效图像恢复的轻量级模块

低级图像恢复是现代人工智能 (AI) 驱动的相机管道的一个组成部分。这些框架中的大多数都基于深度神经网络，这些网络在资源受限的平台（如手机）上呈现出巨大的计算开销。在本文中，我们提出了几个轻量级低级模块，可用于创建给定基线模型的计算成本低的变体。最近关于高效神经网络设计的工作主要集中在分类上。然而，低级图像处理属于“图像到图像”翻译类型，这需要一些分类中不存在的额外计算模块。本文旨在通过设计通用高效模块来弥合这一差距，这些模块可以替代当代基于深度学习的图像恢复网络中使用的基本组件。我们还展示并分析了我们的结果，突出了将深度可分离卷积核（一种用于有效分类网络的流行方法）应用于基于子像素卷积的上采样（一种用于低级视觉应用的流行上采样策略）的缺点。这表明来自分类领域的概念不能总是无缝地集成到“图像到图像”的翻译任务中。我们广泛验证了我们在图像修复、去噪和超分辨率这三个流行任务上的发现。