AI 中文总结
本文针对移动端图像去噪需兼顾复原质量与计算成本、配对数据难采集的问题，提出LiteKD-Net，通过物理引导噪声模拟、适配Real-ESRGAN、特征级知识蒸馏实现高效去噪，性能优于SwinIR。
AI 中文摘要
移动端图像去噪既需要良好的复原质量，又需要较低的计算成本，且采集大规模低质量-高质量（LQ-GT）配对数据十分困难。为此，本文提出LiteKD-Net，一种面向移动端图像去噪的轻量级知识蒸馏网络。首先，采用物理引导的噪声模拟流水线，通过加入像素串扰生成配对训练数据，该流水线与相机所用流水线存在差异。其次，将Real-ESRGAN适配为分辨率一致的去噪模型，并基于深度可分离卷积，使用Lite-RRDB模块构建轻量级学生模型。第三，应用特征级知识蒸馏，在不引入额外推理成本的前提下，将教师模型的复原能力迁移至学生模型。在真实数据集上的实验表明，本文模型在保持良好复原质量的同时，运行时间大幅缩短、推理速率提升，且在所有指标上均优于SwinIR。上述结果表明，LiteKD-Net在复原质量与计算效率间实现了良好的权衡。
英文摘要
Mobile image denoising requires both good restoration quality and low computational cost. In addition, it's annoying to collect large-scale LQ-GT clean pairs. As a result, we propose LiteKD-Net, a lightweight knowledge-distilled network for mobile image denoising. First, a physics-guided noise simulation pipeline generates paired training data by adding pixel crosstalk compared with pipelines applied to cameras. Next, we adapt the Real-ESRGAN to identity-resolution denoising and construct a lightweight Student using Lite-RRDB blocks based on depthwise separable convolutions. Third, feature-level knowledge distillation is applied to transfer the Teacher's restoration capability to the Student without introducing additional inference cost. Experiments on real-world datasets show that our model reaches great reduction in runtime and increase in the inference rate with good restoration quality. Our model also reaches the best in all metrics compared with SwinIR. These results indicate that LiteKD-Net provides a great trade-off between restoration quality and computational efficiency.
