FastSHADE: Fast Self-augmented Hierarchical Asymmetric Denoising for Efficient inference on mobile devices
This paper addresses the need for efficient, high-quality image denoising on mobile devices, a practical deployment challenge for mobile ISP pipelines.
FastSHADE introduces a lightweight U-Net-style network for real-time image denoising on mobile devices, achieving <50 ms latency on a modern mobile GPU while establishing a new state-of-the-art in image quality on the MAI2021 benchmark.
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 a modern mobile GPU) while preserving structural integrity, and our scaled-up FastSHADE-XL establishes a new state-of-the-art for overall image quality. Ultimately, FastSHADE successfully bridges the gap between theoretical network efficiency and practical deployment for real-world mobile ISP pipelines.