A Reference Image Generation Method for Marker-less AR

摘要

In this paper, we present a marker-less AR framework which enables virtual graffiti creation and reference image generation. Our framework also supports 3D annotations such as image textures (virtual graffiti), 3D objects and 3D text, which are superposed over the video stream. We adopt marker-less tracking technique based on key point based descriptors and the trackers. In general, reference image for marker-less AR must be acquired from real image in advance. In such situation, most marker-less tracking approaches force user to capture the front view of a target object. We suppose that reference image does not have to be captured under such condition. In experiments, we showed the estimation accuracy for reference image generation. And we demonstrated real-time marker-less tracking including reference image generation, easy-to-use virtual graffiti creation and immediate superimposing.