9
Performing End-to-End View Synthesis with SynSin
This chapter is dedicated to the latest state-of-the-art view synthesis model called SynSin. View synthesis is one of the main directions in 3D deep learning, which can be used in multiple different domains such as AR, VR, gaming, and more. The goal is to create a model for the given image as an input to reconstruct a new image from another view.
In this chapter, first, we will explore view synthesis and the existing approaches to solving this problem. We will discuss all advantages and disadvantages of these techniques.
Second, we are going to dive deeper into the architecture of the SynSin model. This is an end-to-end model that consists of three main modules. We will discuss each of them ...
Get 3D Deep Learning with Python now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.