Vehicle View Synthesis by Generative Adversarial Network

Abstract

In recent years, novel view synthesis methods has been proposed and combined with many models in different computer vision tasks. Previous works solve the problem by using additional 3D information. In this paper, a novel view synthesis method is proposed based on Generative Adversarial Networks (GANs), named PTGAN. PTGAN generates new views by specifying keypoints of vehicles from other views. This makes the pose transformation of vehicle practical when 3D information is unavailable. The proposed PTGAN first extracts identity-related and pose-unrelated feature representations from input images and then concatenates the representation with the pose information to generate the fake image with the assigned pose to deal with the pose variation problem. Experimental results demonstrate that the proposed method achieves very competitive results to the existing view synthesis methods.