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 avoid redundant information and take into account the scene geometry to determine the depth sampling.

翻译：最近,我们设计了一些学习方法来创建多平面图像(MPIs)来进行视觉合成。尽管多平面图像(MPIs)非常强大,并且便于高质量的投影,但需要大量的内存,使许多应用不切实际。在本文中,我们提出了一个学习方法,优化现有内存,使多平面图像(MPIs)变得紧凑和适应性强。我们的多平面图像(MPIs)避免了多余的信息,并且考虑到现场几何来决定深度取样。