Multiplane Images (MPIs) have shown to be excellent scene representations to synthesize new scene views. Indeed, MPIs are able to model challenging occlusions and reflections, and allow to render novel images in real time and with angular consistency. However, their memory footprint constitutes their major limitation. In this work, we propose a learning-based method that computes compact and adaptive MPIs. Our network promotes sparsity in the MPIs to only keep the necessary scene information. Besides, we adapt the depth sampling to the given scene to optimize the available memory and increase the synthesis quality with a restricted number of planes. Moreover, in contrast to recent work, our approach does not need individual training per scene and is able to generalize well to unseen scenarios. An extensive evaluation shows the superiority of our approach with respect to the state of the art on diverse view synthesis datasets.

多平面图像 (MPI) 已被证明是合成新场景视图的优秀场景表示。事实上，MPI 能够对具有挑战性的遮挡和反射进行建模，并允许实时渲染新颖的图像并且具有角度一致性。然而，它们的内存占用构成了它们的主要限制。在这项工作中，我们提出了一种基于学习的方法来计算紧凑和自适应 MPI。我们的网络促进了 MPI 中的稀疏性，以仅保留必要的场景信息。此外，我们使深度采样适应给定的场景，以优化可用内存并在有限数量的平面上提高合成质量。此外，与最近的工作相比，我们的方法不需要每个场景的单独训练，并且能够很好地泛化到看不见的场景。