Multi-Focus Image Fusion under Strip-Cross Axis Transformer

Multi-focus image fusion technology aims to merge a set of images with different focal lengths into a single clear image, enhancing the integrity of the scene and the visual quality of the image. This paper proposes a multi-focus image fusion method based on the Strip Cross-Axis Transformer (SCT), designed to overcome the limitations of traditional methods and enhance the effectiveness of image fusion. The method utilizes strip feature extraction and a cross-axis attention mechanism to effectively capture both local and global clear region information in the images. Through comparative experiments, we validate that our method achieves better results than traditional methods in multi-focus image fusion tasks, resulting in higher edge clarity and information fidelity.