FaCT-GS: Fast and Scalable CT Reconstruction with Gaussian Splatting

2026-04-02

AI Summary

This work addresses the computational inefficiency and poor scalability of traditional Gaussian Splatting (GS) methods in computed tomography (CT) reconstruction, which struggle with large-scale projection data. The authors propose FaCT-GS, a novel framework that substantially accelerates reconstruction and enhances scalability by deeply optimizing the voxelization and rasterization pipelines and incorporating a prior volume–based warm-start mechanism along with a compressed representation. FaCT-GS achieves the first efficient GS-based reconstruction for large CT projections, delivering over 4× speedup on standard 512×512 projections and more than 13× acceleration on 2K projections compared to the current state-of-the-art GS approaches, thereby establishing a foundation for clinical-grade CT imaging using Gaussian Splatting.

Abstract

Gaussian Splatting (GS) has emerged as a dominating technique for image rendering and has quickly been adapted for the X-ray Computed Tomography (CT) reconstruction task. However, despite being on par or better than many of its predecessors, the benefits of GS are typically not substantial enough to motivate a transition from well-established reconstruction algorithms. This paper addresses the most significant remaining limitations of the GS-based approach by introducing FaCT-GS, a framework for fast and flexible CT reconstruction. Enabled by an in-depth optimization of the voxelization and rasterization pipelines, our new method is significantly faster than its predecessors and scales well with projection and output volume size. Furthermore, the improved voxelization enables rapid fitting of Gaussians to pre-existing volumes, which can serve as a prior for warm-starting the reconstruction, or simply as an alternative, compressed representation. FaCT-GS is over 4X faster than the State of the Art GS CT reconstruction on standard 512x512 projections, and over 13X faster on 2k projections. Implementation available at: https://github.com/PaPieta/fact-gs.

Problem

• Gaussian Splatting
• CT reconstruction
• scalability
• computational efficiency
• X-ray Computed Tomography

Innovation

• Gaussian Splatting
• CT reconstruction
• voxelization optimization
• scalable rendering
• fast reconstruction