Unsupervised Low Light Image Enhancement Using SNR-Aware Swin Transformer
This addresses the problem of improving image quality for low-light conditions in computer vision tasks, but it is incremental as it builds on existing Swin Transformer methods.
The paper tackles low-light image enhancement by proposing a dual-branch Swin Transformer network guided by a signal-to-noise ratio prior map and unsupervised learning based on the Retinex model, achieving competitive performance with baseline models.
Image captured under low-light conditions presents unpleasing artifacts, which debilitate the performance of feature extraction for many upstream visual tasks. Low-light image enhancement aims at improving brightness and contrast, and further reducing noise that corrupts the visual quality. Recently, many image restoration methods based on Swin Transformer have been proposed and achieve impressive performance. However, on one hand, trivially employing Swin Transformer for low-light image enhancement would expose some artifacts, including over-exposure, brightness imbalance and noise corruption, etc. On the other hand, it is impractical to capture image pairs of low-light images and corresponding ground-truth, i.e. well-exposed image in same visual scene. In this paper, we propose a dual-branch network based on Swin Transformer, guided by a signal-to-noise ratio prior map which provides the spatial-varying information for low-light image enhancement. Moreover, we leverage unsupervised learning to construct the optimization objective based on Retinex model, to guide the training of proposed network. Experimental results demonstrate that the proposed model is competitive with the baseline models.