ABSTRACT
Being able to look freely through a scene has long been an active research topic in the computer graphics community. Historically, computer graphics research has been focused on rendering. That is, given a three-dimensional (3D) model, how to generate new images faster, better, and more realistically. View synthesis addresses a typically more challenging problem. It is aimed to generate new images using only a set of two-dimensional (2D) images, instead of 3D models.
