Depth Assisted Full Resolution Network for Single Image-based View Synthesis.

Researches in novel viewpoint synthesis are majorly based on multi-view input images. In this paper, we focus on a more challenging and ill-posed problem that is to synthesize surrounding novel viewpoints from a single image. To achieve this goal, we design a full resolution network to extract fine-scale image fea-tures, which contributes to prevent blurry artifacts. We also involve a pre-trained relative depth estima-tion network, thus 3D information is utilized to infer the flow field between the input and target image. Since the depth network is trained by depth order be-tween any pair of objects, large-scale image features are also involved into our system. Finally, a synthesis layer is used to not only warp the observed pixels to the desired positions but also hallucinate the missing pixels from other recorded pixels. Experiments show that our technique successfully synthesizes reasonable novel viewpoints surrounding the input, while other state-of-the-art techniques fail.