Skip to content

Latest commit

 

History

History
5 lines (3 loc) · 1.32 KB

2312.17142.md

File metadata and controls

5 lines (3 loc) · 1.32 KB

DreamGaussian4D: Generative 4D Gaussian Splatting

Remarkable progress has been made in 4D content generation recently. However, existing methods suffer from long optimization time, lack of motion controllability, and a low level of detail. In this paper, we introduce DreamGaussian4D, an efficient 4D generation framework that builds on 4D Gaussian Splatting representation. Our key insight is that the explicit modeling of spatial transformations in Gaussian Splatting makes it more suitable for the 4D generation setting compared with implicit representations. DreamGaussian4D reduces the optimization time from several hours to just a few minutes, allows flexible control of the generated 3D motion, and produces animated meshes that can be efficiently rendered in 3D engines.

最近在4D内容生成方面取得了显著进展。然而,现有方法存在优化时间长、运动可控性差和细节水平低的问题。在本文中,我们介绍了DreamGaussian4D,这是一个高效的4D生成框架,建立在4D高斯涂抹表征之上。我们的关键洞察是,高斯涂抹中对空间转换的显式建模使其更适合4D生成设置,与隐式表征相比。DreamGaussian4D将优化时间从几小时减少到仅几分钟,允许灵活控制生成的3D运动,并产生可以在3D引擎中高效渲染的动画网格。