轻量级图像去噪模型，移动端实时高保真降噪
FastSHADE: Fast Self-augmented Hierarchical Asymmetric Denoising for Efficient inference on mobile devices
- 分阶段架构+异构频域块，分离结构与高频噪声处理
- 基线版<50毫秒延迟，极限版达37.94 dB PSNR新高
- 自增强数据策略提升泛化性，适合移动设备部署
实时图像去噪对现代移动摄影至关重要，但受限于边缘设备的严格延迟和功耗约束。本文提出FastSHADE（快速自增强分层非对称去噪），一种专为移动GPU设计的轻量级U-Net风格网络，实现高效、高保真恢复。方法采用多阶段架构，引入新型异构频域去噪块（AFDB），将空间结构提取与高频噪声抑制解耦以提升效率；并设计空间门控上采样器（SGU）优化高分辨率跳跃连接融合。为增强泛化能力，提出高效的噪声位移自增强策略，在不引入领域偏移的前提下提升数据多样性。在MAI2021基准上的评估表明，可扩展的模型家族实现了极优的速度-保真度权衡：基础版FastSHADE-M在Adreno 840 GPU上保持<50毫秒实时延迟，同时保留结构完整性；扩大版FastSHADE-XL在整体图像质量上达到新纪录，取得37.94 dB PSNR。
原文摘要 · Abstract (English)
Real-time image denoising is essential for modern mobile photography but remains challenging due to the strict latency and power constraints of edge devices. This paper presents FastSHADE (Fast Self-augmented Hierarchical Asymmetric Denoising), a lightweight U-Net-style network tailored for real-time, high-fidelity restoration on mobile GPUs. Our method features a multi-stage architecture incorporating a novel Asymmetric Frequency Denoising Block (AFDB) that decouples spatial structure extraction from high-frequency noise suppression to maximize efficiency, and a Spatially Gated Upsampler (SGU) that optimizes high-resolution skip connection fusion. To address generalization, we introduce an efficient Noise Shifting Self-Augmentation strategy that enhances data diversity without inducing domain shifts. Evaluations on the MAI2021 benchmark demonstrate that our scalable model family establishes a highly efficient speed-fidelity trade-off. Our base FastSHADE-M variant maintains real-time latency (<50 ms on an Adreno 840 GPU) while preserving structural integrity, and our scaled-up FastSHADE-XL establishes a new state-of-the-art for overall image quality, achieving 37.94 dB PSNR.
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。