DreamGaussian4D：生成式4D高斯點降

DreamGaussian4D: Generative 4D Gaussian Splatting

December 28, 2023

作者: Jiawei Ren, Liang Pan, Jiaxiang Tang, Chi Zhang, Ang Cao, Gang Zeng, Ziwei Liu

cs.AI

摘要

最近在4D內容生成方面取得了顯著進展。然而，現有方法存在優化時間長、運動可控性不足和細節水平低的問題。本文介紹了DreamGaussian4D，這是一個高效的4D生成框架，基於4D高斯Splatting表示法。我們的關鍵洞察是，在高斯Splatting中對空間變換進行明確建模，使其與隱式表示法相比更適合4D生成設置。DreamGaussian4D將優化時間從數小時縮短到幾分鐘，允許靈活控制生成的3D運動，並生成可在3D引擎中高效渲染的動畫網格。

English

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.