Glow in the Dark: Low-Light Image Enhancement With External Memory

Deep learning-based methods have achieved remarkable success with powerful modeling capabilities. However, the weights of these models are learned over the entire training dataset, which inevitably leads to the ignorance of sample specific properties in the learned enhancement mapping. This situation causes ineffective enhancement in the testing phase for the samples that differ significantly from the training distribution. In this paper, we introduce external memory to form an external memory-augmented network (EMNet) for low-light image enhancement. The external memory aims to capture the sample specific properties of the training dataset to guide the enhancement in the testing phase. Benefiting from the learned memory, more complex distributions of reference images in the entire dataset can be “remembered” to facilitate the adjustment of the testing samples more adaptively. To further augment the capacity of the model, we take the transformer as our baseline network, which specializes in capturing long-range spatial redundancy. Experimental results demonstrate that our proposed method has a promising performance and outperforms state-of-the-art methods. It is noted that, the proposed external memory is a plug-and-play mechanism that can be integrated with any existing method to further improve the enhancement quality. More practices of integrating external memory with other image enhancement methods are qualitatively and quantitatively analyzed. The results further confirm that the effectiveness of our proposed memory mechanism when combing with existing enhancement methods.

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.