Seam-Driven Image Stitching

Abstract

Image stitching computes geometric transforms to align images based on the best fit of feature correspondences between overlapping images. Seam-cutting is used afterwards to to hide misalignment artifacts. Interestingly it is often the seam-cutting step that is the most crucial for obtaining a perceptually seamless result. This motivates us to propose a seam-driven image stitching strategy where instead of estimating a geometric transform based on the best fit of feature correspondences, we evaluate the goodness of a transform based on the resulting visual quality of the seam-cut. We show that this new image stitching strategy can often produce better perceptual results than existing methods especially for challenging scenes.