This paper proposes a novel multi-focus image fusion algorithm. Different from traditional decision map based methods, our algorithm is based on salience preserving gradient, which can better emphasize the structure details of sources while preserving the color consistency. We firstly measure the salience map of the gradient from each source, and then use their saliency to modulate their contributions in computing the global statistics. Gradients with high saliency are properly highlighted in the target gradient, and thereby salient features in the sources are well preserved. Furthermore we extend it to color domain by proposing an importance-weight based trigonometric average method to merge the color components. Extensive experiments on several datasets have demonstrated the effectiveness of our approach.