Real-time Stereo-Image Stitching using GPU-based Belief Propagation

Image stitching or mosaicing is a challenging vi- sion problem, especially when considering aspects like high definition content, real-time, and proper compensation of the parallax error of objects at dif- ferent distances to the camera system. Today many approaches to image stitching exist, most of them deal with medium resolution images, offline pro- cessing, or are restricted to objects at similar dis- tance. Our approach is based on calculation of dis- parities between corresponding points in stereo im- ages by employing standard belief propagation. In- stead of computing depth-maps like in previous ap- proaches, we compute stitch-maps modifying cost functions in the underlying Markov random field model, which makes further projection steps dis- pensable and thereby overall computation more ef- ficient. Our GPU-based implementation is real-time capable, allowing to stitch high definition images at constant frame rates. We show exemplary results from our system to demonstrate the quality of the merged images.