CoGS: Controllable Gaussian Splatting
This addresses the challenge of practical 3D scene manipulation for applications like animation or VR, though it appears incremental as it builds on 3D Gaussian Splatting.
The paper tackles the problem of capturing and re-animating 3D articulated objects by introducing CoGS, a method for Controllable Gaussian Splatting that enables real-time control of dynamic scenes without pre-computed signals, and it outperforms existing methods in visual fidelity on synthetic and real-world datasets.
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, existing methods for 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.