TL;DR本文旨在从多视角视频中建模 3D 场景的动态。我们提出了一种新的方法,通过仅利用视频帧学习 3D 场景的几何、外观和物理速度,从而支持多种理想的应用,包括未来帧插值、无监督的 3D 语义场景分解和动态运动传递。
Abstract
In this paper, we aim to model 3d scene dynamics from multi-view videos.
Unlike the majority of existing works which usually focus on the common task of
novel view synthesis within the training time period, we pr