用硬件感知NAS优化移动端去噪模型，兼顾速度与精度。
Mobile-friendly Image de-noising: Hardware Conscious Optimization for Edge Application
- 基于熵正则化可微架构搜索，设计适配手机的U-Net去噪网络。
- 参数少12%，延迟减半，内存降低50%，仅损失0.7% PSNR。
- 适合资源受限的边缘设备部署，通用性强，实测表现优。
图像增强在计算机视觉与摄影中至关重要，但噪声问题使得传统图像信号处理（ISP）方法难以应对深度学习的进展。当前方法的成功越来越依赖于其在边缘设备（如智能手机）上的部署便利性。本文提出首个面向移动设备的去噪网络，采用熵正则化的可微神经架构搜索（NAS），在硬件感知的搜索空间中对U-Net架构进行优化。该模型参数减少12%，在三星Galaxy S24 Ultra上实现约2倍的推理延迟降低和1.5倍的内存占用缩减，仅导致PSNR下降0.7%。相比当前最优的Swin-Transformer图像恢复模型，本方法在保持相近精度的同时，计算量（GMACs）降低约18倍。模型在4个基准数据集上成功验证了对三种高斯噪声强度的去噪能力，并在1个真实场景数据集上实现良好泛化性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。