Practical Deep Raw Image Denoising on Mobile Devices
This work addresses the practical challenge of deploying high-quality image denoising on mobile devices, enabling features like night shot in smartphones, though it is incremental in optimizing existing methods for mobile constraints.
The paper tackles the problem of computationally expensive deep learning-based image denoising for mobile devices by proposing a lightweight neural network that runs efficiently on mobile hardware, achieving high-quality results with a runtime of ~70 milliseconds per megapixel on a Snapdragon 855 chipset.
Deep learning-based image denoising approaches have been extensively studied in recent years, prevailing in many public benchmark datasets. However, the stat-of-the-art networks are computationally too expensive to be directly applied on mobile devices. In this work, we propose a light-weight, efficient neural network-based raw image denoiser that runs smoothly on mainstream mobile devices, and produces high quality denoising results. Our key insights are twofold: (1) by measuring and estimating sensor noise level, a smaller network trained on synthetic sensor-specific data can out-perform larger ones trained on general data; (2) the large noise level variation under different ISO settings can be removed by a novel k-Sigma Transform, allowing a small network to efficiently handle a wide range of noise levels. We conduct extensive experiments to demonstrate the efficiency and accuracy of our approach. Our proposed mobile-friendly denoising model runs at ~70 milliseconds per megapixel on Qualcomm Snapdragon 855 chipset, and it is the basis of the night shot feature of several flagship smartphones released in 2019.