I. Introduction
Under-exposure is a common unavoidable condition in degrading image quality. Such images often suffer from poor visibility, intensive noise, color cast, etc., which hinder human vision perception. Although the exposure adjustment (e.g., high ISO, long exposure, flashlight) can be applied to enhance image brightness, it also introduces other drawbacks (e.g., noise, blur, over-saturation). Besides, lower visibility may also hamper high-level computer vision applications [1]. Hence, it is critical to develop intelligent and practical algorithms for effective and efficient low-light image enhancement.