仅4000参数的轻量级CNN，实现手机端每秒1100帧的实时图像增强。
MobileIE: An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devices
- 结合重参数化与增量权重优化，极小化模型体积与计算开销。
- 在多个图像增强任务中达成1100帧/秒的实时推理速度，效果领先。
- 适合移动端部署，兼顾速度与图像质量，尤其适合实时应用。
深度神经网络推动了图像增强（IE）的显著进展，但其在资源受限设备（如移动设备）上的部署仍面临高计算与内存需求的挑战。为解决这一问题并实现在移动设备上的实时图像增强，本文提出一种超轻量级卷积神经网络（CNN）框架，参数量约为4000个。该方法结合重参数化与增量权重优化策略以保障效率，并引入特征自变换模块与分层双路径注意力机制，采用局部方差加权损失进行优化。基于此高效框架，首次实现高达1100帧/秒（FPS）的实时图像增强推理，同时保持优异的图像质量，在多项任务中达到速度与性能的最佳平衡。代码将开源至 https://github.com/AVC2-UESTC/MobileIE.git。
原文摘要 · Abstract (English)
Recent advancements in deep neural networks have driven significant progress in image enhancement (IE). However, deploying deep learning models on resource-constrained platforms, such as mobile devices, remains challenging due to high computation and memory demands. To address these challenges and facilitate real-time IE on mobile, we introduce an extremely lightweight Convolutional Neural Network (CNN) framework with around 4K parameters. Our approach integrates reparameterization with an Incremental Weight Optimization strategy to ensure efficiency. Additionally, we enhance performance with a Feature Self-Transform module and a Hierarchical Dual-Path Attention mechanism, optimized with a Local Variance-Weighted loss. With this efficient framework, we are the first to achieve real-time IE inference at up to 1,100 frames per second (FPS) while delivering competitive image quality, achieving the best trade-off between speed and performance across multiple IE tasks. The code will be available at https://github.com/AVC2-UESTC/MobileIE.git.
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。