CoGS: Controllable Gaussian Splatting
Preprint
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, 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.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction2024
- VolTeMorph: Real‐time, Controllable and Generalizable Animation of Volumetric RepresentationsComputer Graphics Forum, 2024
- Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis2024
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingACM Transactions on Graphics, 2023
- Fast Dynamic Radiance Fields with Time-Aware Neural Voxels2022
- Instant neural graphics primitives with a multiresolution hash encodingACM Transactions on Graphics, 2022
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004