Neural Rendering of object-based audio-visual scenes

本研究将探讨使用神经渲染方法从基于对象的表示中渲染具有视频真实感的一般动态场景。学习到的自然空间和时间外观的表示将通过深度网络架构（GAN， VAE等）用于实时渲染场景。目标是从视频捕获的基于对象的场景表示中复制自然场景的高度逼真的内容。

This research will investigate the use of neural rendering methods to render general dynamic scenes from object-based representations with the realism of video. Learnt representations of natural spatial and temporal appearance will be exploited through deep network architectures (GAN, VAE etc.) for real time rendering of scenes. The goal is to enable the reproduction of highly-realistic content for natural scenes from object based scene representations derived from video capture.