R2-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction

Ruyi Zha1, Tao Jun Lin1, Yuanhao Cai2, Jiwen Cao1, Yanhao Zhang3, Hongdong Li1,
1Australian National University, 2Johns Hopkins University, 3University of Technology Sydney
Paper arXiv Code
cover

R2-Gaussian is a 3DGS-based framework for fast CT reconstruction.

Abstract

3D Gaussian splatting (3DGS) has shown promising results in image rendering and surface reconstruction. However, its potential in volumetric reconstruction tasks, such as X-ray computed tomography, remains under-explored. This paper introduces R2-Gaussian, the first 3DGS-based framework for sparse-view tomographic reconstruction. By carefully deriving X-ray rasterization functions, we discover a previously unknown integration bias in the standard 3DGS formulation, which hampers accurate volume retrieval. To address this issue, we propose a novel rectification technique via refactoring the projection from 3D to 2D Gaussians. Our new method presents three key innovations: (1) introducing tailored Gaussian kernels, (2) extending rasterization to X-ray imaging, and (3) developing a CUDA-based differentiable voxelizer. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches by 0.93 dB in PSNR and 0.014 in SSIM. Crucially, it delivers high-quality results in 3 minutes, which is 12x faster than NeRF-based methods and on par with traditional algorithms. The superior performance and rapid convergence of our method highlight its practical value.

Pipeline

pipeline

Qualitative Results

Human Organs

Animals and Plants

Artificial Objects

BibTeX

@misc{zha2024r2gaussian,
      title={R$^2$-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction}, 
      author={Ruyi Zha and Tao Jun Lin and Yuanhao Cai and Jiwen Cao and Yanhao Zhang and Hongdong Li},
      year={2024},
      eprint={2405.20693},
      archivePrefix={arXiv},
      primaryClass={eess.IV}
}