Skip to yearly menu bar Skip to main content


Poster

CoGS: Controllable Gaussian Splatting

Heng Yu · Joel Julin · Zoltán Á. Milacski · Koichiro Niinuma · László A. Jeni

Arch 4A-E Poster #200
[ ] [ Project Page ] [ Paper PDF ]
[ Poster
Fri 21 Jun 10:30 a.m. PDT — noon PDT

Abstract:

Capturing and re-animating the 3D structure of articulated objects present significant barriers. On one hand, methods requiring extensively calibrated multi-view setups are prohibitively complex and resource-intensive, limiting their practical applicability. On the other hand, while single-camera Neural Radiance Fields (NeRFs) offer a more streamlined approach, they have excessive training and rendering costs. 3D Gaussian Splatting would be a suitable alternative, but for two reasons. Firstly, 3D dynamic Gaussians require synchronized multi-view cameras, and secondly, the lack of controllability in dynamic scenarios. We present CoGS, a method for Controllable Gaussian Splatting, that enables the direct manipulation of scene elements, offering real-time control of dynamic scenes without the prerequisite of pre-computing control signals. We evaluated CoGS using both synthetic and real-world datasets that include dynamic objects that differ in degree of difficulty.In our evaluations, CoGS consistently outperformed existing dynamic and controllable neural representations in terms of visual fidelity.

Chat is not available.