Recurrent Enhancement of Visual Comfort for Casual Stereoscopic Photography

Creating stereoscopic 3D media content has wide applications in virtual reality. In this paper, we are interested in a challenging application, casual stereoscopic photography, that allows ordinary users to create a stereoscopic photo using two images captured by a hand-held monocular camera. To handle the geometric constraints and disparity adjustment for casually captured left and right images, we present a coarse-to-fine framework. In the coarse stage, we propose a unified reinforcement learning-based method, in which the produced stereo image is iteratively adjusted and evaluated in the term of visual comfort. In addition, to further enhance the visual comfort of the stereoscopic image produced in the coarse stage, we introduce another independent recurrent network to fine-tune its disparity range. Lastly, we perform comprehensive experiments to evaluate our method and demonstrate the applicability of our model for real images.