Turbo-GS：加速高分辨率辐射场的三维高斯拟合
Turbo-GS: Accelerating 3D Gaussian Fitting for High-Resolution Radiance Fields
针对高分辨率场景下 3DGS 拟合慢的问题，提出稀疏像素渲染（dilated rendering）与收敛感知的预算控制，可直接迁移到任何需要加速高斯泼溅训练或高分辨率辐射场重建的流程中。
原文依据 we introduce a dilated rendering technique that renders only a subset of pixels instead of the full image
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论新视角合成在计算机视觉中具有重要作用，广泛应用于三维重建、混合现实和机器人等领域。近期的方法如三维高斯泼溅（3DGS）已成为最优方案，能够实时提供高质量的新视角合成。然而，3DGS 模型的训练仍然缓慢，尤其对于高分辨率图像，拟合一个包含 200 个视角的场景往往需要数小时。在本工作中，我们旨在通过降低计算开销和提升学习效率来加速拟合过程。具体而言，我们引入一种空洞渲染技术，仅渲染部分像素而非整幅图像，从而显著降低计算成本。为提升学习效率，我们设计了一种收敛感知的预算控制机制，用于平衡新增高斯与已有高斯优化之间的关系。此外，为提升致密化效率并防止梯度消失，我们同时引入位置误差与外观误差以增强致密化效果。借助这些改进，我们在保持甚至提升新视角渲染质量的同时，实现了快速的 4K 分辨率拟合。大量实验表明，我们的方法在保持高渲染保真度的同时，优化速度显著快于现有方法。
英文原文摘要 1352 字符
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 error to enhance densification effectiveness. 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.