Low Light Image Enhancement via Global and Local Context Modeling
This work provides an incremental improvement in low-light image enhancement for computer vision applications.
This paper addresses the problem of low-light image enhancement, where images suffer from poor visibility, low contrast, and lack of color vividness. The authors propose a context-aware deep network that models both global and local spatial correlations. Their method achieves state-of-the-art performance on three datasets, improving PSNR from 23.04 dB to 24.45 dB on the MIT-Adobe FiveK dataset.
Images captured under low-light conditions manifest poor visibility, lack contrast and color vividness. Compared to conventional approaches, deep convolutional neural networks (CNNs) perform well in enhancing images. However, being solely reliant on confined fixed primitives to model dependencies, existing data-driven deep models do not exploit the contexts at various spatial scales to address low-light image enhancement. These contexts can be crucial towards inferring several image enhancement tasks, e.g., local and global contrast, brightness and color corrections; which requires cues from both local and global spatial extent. To this end, we introduce a context-aware deep network for low-light image enhancement. First, it features a global context module that models spatial correlations to find complementary cues over full spatial domain. Second, it introduces a dense residual block that captures local context with a relatively large receptive field. We evaluate the proposed approach using three challenging datasets: MIT-Adobe FiveK, LoL, and SID. On all these datasets, our method performs favorably against the state-of-the-arts in terms of standard image fidelity metrics. In particular, compared to the best performing method on the MIT-Adobe FiveK dataset, our algorithm improves PSNR from 23.04 dB to 24.45 dB.