Computed Tomography (CT) enables detailed cross-sectional imaging but continues to face challenges in balancing reconstruction quality and computational efficiency. While deep learning-based methods have significantly improved image quality and noise reduction, they typically require large-scale training data and intensive computation. Recent advances in scene reconstruction, such as Neural Radiance Fields and 3D Gaussian Splatting, offer alternative perspectives but are not well-suited for direct volumetric CT reconstruction. In this work, we propose Discretized Gaussian Representation (DGR), a novel framework that reconstructs the 3D volume directly using a set of discretized Gaussian functions in an end-to-end manner. To further enhance efficiency, we introduce Fast Volume Reconstruction, a highly parallelized technique that aggregates Gaussian contributions into the voxel grid with minimal overhead. Extensive experiments on both real-world and synthetic datasets demonstrate that DGR achieves superior reconstruction quality and runtime performance across various CT reconstruction scenarios. Our code is publicly available at https://github.com/wskingdom/DGR.
@article{arxiv.2411.04844,
title = {Discretized Gaussian Representation for Tomographic Reconstruction},
author = {Shaokai Wu and Yuxiang Lu and Yapan Guo and Wei Ji and Suizhi Huang and Fengyu Yang and Shalayiding Sirejiding and Qichen He and Jing Tong and Yanbiao Ji and Yue Ding and Hongtao Lu},
journal= {arXiv preprint arXiv:2411.04844},
year = {2025}
}