Depth-based image mosaicing for both static and dynamic scenes

Traditional image-based mosaicing deals with the problem of parallax by imposing constraints of a parallax-free camera configuration or requiring a dense sampling of the scene. These solutions are often impractical or fail to address the needs of the application. Instead, taking advantage of depth cues and a criterion of smooth transitions, we achieve significantly improved mosaicing results for static scenes, coping effectively with non-trivial parallax in the input. Furthermore, by incorporating a criterion of consistent motion perception, we demonstrate progress on mosaicing of dynamic scenes without introducing artifacts. Although further additions are required to cope with unconstrained object motion, our algorithm can synthesize perceptually convincing dynamic mosaics, conveying the same appearance of object motion as seen in the original sequences.