- Research & Innovation
- Thought Leadership
- About Us
- Investors
-
Recently, learning methods have been designed to create Multiplane Images (MPIs) for view synthesis. While MPIs are extremely powerful and facilitate high quality renderings, a great amount of memory is required, making them impractical for many applications. In this paper, we propose a learning method that optimizes the available memory to render compact and adaptive MPIs. Our MPIs avoids redundant information and takes into account the scene geometry to determine the depth sampling.
