Building Stereoscopic Zoomer via Global and Local Warping Optimization

Magnifying left and right images by increasing focal length of optical zoom lenses is a direct way for stereoscopic zoom. However, without adjusting the baseline distance, the optical zoom may distort the three-dimensional (3D) perception. To tackle this problem, this article presents a stereoscopic zoomer that directly operates on image plane by synthesizing a virtual camera in depth direction to simulate the zoom process. Specifically, we propose a two-stage warping optimization framework for zooming, which is solved by imposing global and local energy constraints. Different from the existing 3D rendering methods, the important innovation of our method is to take content zoom, depth adaptation and user editability into account in mesh optimization. Experimental results demonstrate that our method can achieve promising zoom effect on daily person scenes and street views.