Locally Adaptive Channel Attention-Based Spatial-Spectral Neural Network for Image Deblurring

Recently, due to the rapid development of deep neural networks in the field of computer vision, many studies have been conducted in the field of image deblurring. However, previous methods cannot attain satisfactory deblurring performance in object boundaries and local regions containing image details in restored results. This paper proposes a new method that uses a locally adaptive channel attention module for a spectral-spatial network to resolve the problem of single-image deblurring. Unlike existing methods, our proposed method consists of a spectral restorer and spatial restorer that adopt a locally adaptive attention mechanism in the spectral-spatial domains. In addition, unlike a conventional spectral-spatial network that only considers the magnitude of the frequency coefficients, the proposed method uses both the magnitude and phase of the frequency coefficients in the training stage. Our locally adaptive channel attention spectral-spatial network can focus on informative channels that are closely related to blur artifacts. Specifically, the spatial restorer, which guides the intensity of the blur image to fit the ground truth by exploring the interdependencies of feature channels, can efficiently restore scene characteristics while the spectral restorer, which guides the magnitude and phase of the blur image's frequency coefficients to fit those of the ground truth by exploring the interdependencies of feature channels, fine-tunes the details of structures. The experimental results show that the proposed method outperformed the deblurring results compared to benchmark methods in terms of both qualitative evaluation and quantitative metrics.