Turbo-GS: Accelerating 3D Gaussian Fitting for High-Quality Radiance Fields

TL;DR

Turbo-GS introduces techniques to significantly accelerate 3D Gaussian fitting for high-resolution radiance fields, enabling faster training without sacrificing rendering quality.

Contribution

The paper proposes a dilated rendering method and a convergence-aware control mechanism to improve efficiency and speed in 3D Gaussian scene fitting.

Findings

Achieves fast 4K-resolution fitting with high fidelity

Reduces computational costs by rendering fewer pixels

Maintains or improves rendering quality with faster optimization

Abstract

Novel-view synthesis plays a crucial role in computer vision with applications in 3D reconstruction, mixed reality, and robotics. Recent approaches, such as 3D Gaussian Splatting (3DGS), have emerged as state-of-the-art solutions, offering high-quality novel view synthesis in real time. However, training 3DGS models remains slow, particularly for high-resolution images, often requiring hours to fit a scene with 200 views. In this work, we aim to accelerate the fitting process by reducing computational overhead and improving learning efficiency. Specifically, we introduce a dilated rendering technique that renders only a subset of pixels instead of the full image, significantly reducing computational costs. To enhance learning efficiency, we develop a convergence-aware budget control mechanism that balances the addition of new Gaussians with the optimization of existing ones. Additionally, to improve densification efficiency and prevent gradient vanishing, we incorporate both positional and appearance errors to improve the effectiveness of densification. With these improvements, we achieve fast 4K-resolution fitting while maintaining, or even improving, novel view rendering quality. Extensive experiments demonstrate that our method achieves significantly faster optimization than existing approaches while preserving high rendering fidelity.