移动端图像去噪：面向边缘应用的硬件感知优化
Mobile-friendly Image de-noising: Hardware Conscious Optimization for Edge Application
AI总结：
本文提出了一种基于硬件感知优化的移动端图像去噪网络，通过熵正则化的可微神经架构搜索实现参数减少和性能提升，同时在多个基准测试中展示了其去噪能力和泛化能力。
摘要：
图像增强是计算机视觉和摄影中的关键任务，通常与噪声交织在一起。这使得传统的图像信号处理（ISP）在深度学习的进步面前显得无能为力。然而，这些方法的成功越来越与它们在边缘设备（如智能手机）上的部署难度相关。本文提出了一种新的移动友好的网络用于图像去噪，通过在硬件感知的搜索空间上使用熵正则化的可微神经架构搜索（NAS）来获得U-Net架构，这是首次尝试。设计的模型参数减少了12%，在部署和分析上智能手机S24 Ultra上，设备延迟提高了约2倍，内存占用提高了1.5倍，而PSNR下降了0.7%。与SOTA Swin-Transformer图像修复相比，所提出的网络在准确性上具有竞争力，GMACs减少了约18倍。此外，该网络在三种强度的高斯去噪上通过了四个基准测试，并在一项基准测试上成功进行了现实世界的去噪，展示了其泛化能力。
英文摘要：
Image enhancement is a critical task in computer vision and photography that is often entangled with noise. This renders the traditional Image Signal Processing (ISP) ineffective compared to the advances in deep learning. However, the success of such methods is increasingly associated with the ease of their deployment on edge devices, such as smartphones. This work presents a novel mobile-friendly network for image de-noising obtained with Entropy-Regularized differentiable Neural Architecture Search (NAS) on a hardware-aware search space for a U-Net architecture, which is first-of-its-kind. The designed model has 12% less parameters, with ~2-fold improvement in ondevice latency and 1.5-fold improvement in the memory footprint for a 0.7% drop in PSNR, when deployed and profiled on Samsung Galaxy S24 Ultra. Compared to the SOTA Swin-Transformer for Image Restoration, the proposed network had competitive accuracy with ~18-fold reduction in GMACs. Further, the network was tested successfully for Gaussian de-noising with 3 intensities on 4 benchmarks and real-world de-noising on 1 benchmark demonstrating its generalization ability.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
