Edgeconstrained image compositing

The classic task of image compositing is complicated by the fact that the source and target images need to be carefully aligned and adjusted. Otherwise, it is not possible to achieve convincing results. Visual artifacts are caused by image intensity mismatch, image dis-tortion or structure misalignment even if the images have been glob-ally aligned. In this paper we extend classic Poisson blending by a constrained structure deformation and propagation method. This approach can solve the above-mentioned problems and proves use-ful for a variety of applications, e.g. in de-ghosting of mosaic im-ages, classic image compositing or other applications such as super-resolution from image databases. Our method is based on the fol-lowing basic steps. First, an optimal partitioning boundary is com-puted between the input images. Then, features along this boundary are robustly aligned and deformation vectors are computed. Start-ing at these features, salient edges are traced and aligned, serving as additional constraints for the smooth deformation field, which is propagated robustly and smoothly into the interior of the target im-age. If very different images are to be stitched, we propose to base the deformation constraints on the curvature of the salient edges for C1-continuity of the structures between the images