Though recent years have witnessed remarkable progress in single image super-resolution (SISR) tasks with the prosperous development of deep neural networks (DNNs), the deep learning methods are confronted with the computation and memory consumption issues in practice, especially for resource-limited platforms such as mobile devices. To overcome the challenge and facilitate the real-time deployment of SISR tasks on mobile, we combine neural architecture search with pruning search and propose an automatic search framework that derives sparse super-resolution (SR) models with high image quality while satisfying the real-time inference requirement. To decrease the search cost, we leverage the weight sharing strategy by introducing a supernet and decouple the search problem into three stages, including supernet construction, compiler-aware architecture and pruning search, and compiler-aware pruning ratio search. With the proposed framework, we are the first to achieve real-time SR inference (with only tens of milliseconds per frame) for implementing 720p resolution with competitive image quality (in terms of PSNR and SSIM) on mobile platforms (Samsung Galaxy S20).

翻译：尽管近年来随着深度神经网络（DNNs）的蓬勃发展，单图像超分辨率（SISR）任务取得了显著进展，但深度学习方法在实际应用中面临着计算和内存消耗问题，尤其是在移动设备等资源受限平台上。为克服这一挑战并实现SISR任务在移动端的实时部署，我们将神经架构搜索与剪枝搜索相结合，提出了一种自动搜索框架，能够在满足实时推理要求的同时，生成具有高图像质量的稀疏超分辨率（SR）模型。为降低搜索成本，我们利用权重共享策略引入超网络，并将搜索问题解耦为三个阶段，包括超网络构建、编译器感知的架构与剪枝搜索，以及编译器感知的剪枝比例搜索。通过所提出的框架，我们首次在移动平台（三星Galaxy S20）上实现了720p分辨率的实时SR推理（每帧仅需几十毫秒），并取得了具有竞争力的图像质量（以PSNR和SSIM衡量）。