arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.10086cs.CV
收藏

用于视图合成的紧凑和自适应多平面图像

Compact and adaptive multiplane images for view synthesis

InterDigital

Julia Navarro, Neus Sabater

摘要:

最近,已经设计了学习方法来创建用于视图合成的多平面图像(MPI)。虽然MPI功能非常强大,可以促进高质量的渲染,但需要大量的内存,这使得它们对许多应用程序来说不切实际。在本文中,我们提出了一种学习方法,优化可用的内存,使紧凑和自适应MPI。我们的MPI避免了冗余信息,并考虑到场景的几何形状来确定深度采样。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑