Photo Stand-Out: Photography with Virtual Character

Extended augmented reality techniques and applications of virtual characters, like taking photography with a female warrior in Sci-Fi museum, provide a diverse and immersive experience in the real world. In different scenes, the virtual character should be posed naturally with the user, expressing an aesthetic pose, to obtain photography with the personalized posed virtual character rather than that with the immutable pre-designed pose. In this paper, we propose a novel optimization framework to synthesize an aesthetic pose for the virtual character with respect to the presented user's pose. Our approach applies aesthetic evaluation that exploits fully connected neural networks trained on example images. The aesthetic pose of the virtual character is obtained by optimizing a cost function that guides the rotation of each body joint angles. In our experiments, we demonstrate the proposed approach can synthesize poses for virtual characters according to user pose inputs. We also conducted objective and subjective experiments of the synthesized results to validate the efficacy of our approach.