StripWinformer: Locally-Enhanced Transformer for Image Motion Deblurring

Single image motion deblurring is a critical low-level computer vision task, aiming to restore clear and sharp images from motion-corrupted counterparts. To address the limitations of traditional image motion deblurring methods, which often struggle to handle complex motion patterns and preserve fine details, we propose a novel framework inspired by the success of vision transformers. Our approach leverages the power of transformers to capture motion blurred patterns both locally and globally. To alleviate the computational burden, many vision transformer techniques adopt a strategy of partitioning the image into multiple windows and subsequently modeling the relationships within each isolated window. Nonetheless, these approaches impose limitations on the exchange of information among the windows, hindering the overall performance. In this paper, we present a transformer block including partitioning the image into horizontal and vertical strips to capture long-range blur patterns, along with the use of windows to capture short-range blur patterns. To further expand the receptive field of the transformer, we employ an efficient mechanism that specifically emphasizes the correlation between different windows. This design effectively addresses the limitation of insufficient information exchange across windows in conventional transformer approaches. To assess the effectiveness of our model, we conduct evaluation on several single image motion deblurring datasets. The result of our evaluation demonstrate that the proposed architecture achieves competitive performance compared to other state-of-the-art approaches in the field of motion deblurring.