mlsanityData to 14 Oct 2026

3DGR-CT: Sparse-View CT Reconstruction with a 3D Gaussian Representation

arXiv 2312.15676 ↗First posted 25 Dec 2023eess.IV cs.CVcited by 25

Not on the map. Why?

Abstract (arXiv)

Sparse-view computed tomography (CT) reduces radiation exposure by acquiring fewer projections, making it a valuable tool in clinical scenarios where low-dose radiation is essential. However, this often results in increased noise and artifacts due to limited data. In this paper we propose a novel 3D Gaussian representation (3DGR) based method for sparse-view CT reconstruction. Inspired by recent success in novel view synthesis driven by 3D Gaussian splatting, we leverage the efficiency and expressiveness of 3D Gaussian representation as an alternative to implicit neural representation. To unleash the potential of 3DGR for CT imaging scenario, we propose two key innovations: (i) FBP-image-guided Guassian initialization and (ii) efficient integration with a differentiable CT projector. Extensive experiments and ablations on diverse datasets demonstrate the proposed 3DGR-CT consistently outperforms state-of-the-art counterpart methods, achieving higher reconstruction accuracy with faster convergence. Furthermore, we showcase the potential of 3DGR-CT for real-time physical simulation, which holds important clinical applications while challenging for implicit neural representations.

Key facts. Cited by 25 papers in the map (data through 14 Oct 2026). Builds on 34 of its 67 references that are in the map. First posted on arXiv 25 Dec 2023.

Builds on

34 of 67 references.

References · 34

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  3. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  4. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  5. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  6. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,416
  7. 2018On the Spectral Bias of Neural Networkscited by 1,341
  8. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 521
  9. 2023PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamicscited by 377
  10. 2023GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splattingcited by 335
  11. 2023EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingScited by 196
  12. 2023Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Modelscited by 157
22 more
  1. 2021NeRP: Implicit Neural Representation Learning with Prior Embedding for Sparsely Sampled Image Reconstructioncited by 146
  2. 2022Solving 3D Inverse Problems using Pre-trained 2D Diffusion Modelscited by 132
  3. 2023CompGS: Smaller and Faster Gaussian Splatting with Vector Quantizationcited by 130
  4. 2020VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Imagescited by 111
  5. 2022NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstructioncited by 108
  6. 2023Implicit Neural Representation in Medical Imaging: A Comparative Surveycited by 90
  7. 2021Dynamic CT Reconstruction from Limited Views with Implicit Neural Representations and Parametric Motion Fieldscited by 71
  8. 2023SynthRAD2023 Grand Challenge dataset: generating synthetic CT for radiotherapycited by 53
  9. 2018Deep-neural-network based sinogram synthesis for sparse-view CT image reconstructioncited by 47
  10. 2023Learning Deep Intensity Field for Extremely Sparse-View CBCT Reconstructioncited by 42
  11. 2021CoIL: Coordinate-based Internal Learning for Imaging Inverse Problemscited by 33
  12. 2017Lose The Views: Limited Angle CT Reconstruction via Implicit Sinogram Completioncited by 31
  13. 2021A Computed Tomography Vertebral Segmentation Dataset with Anatomical Variations and Multi-Vendor Scanner Datacited by 28
  14. 2023FreeSeed: Frequency-band-aware and Self-guided Network for Sparse-view CT Reconstructioncited by 21
  15. 2021Task-Oriented Low-Dose CT Image Denoisingcited by 11
  16. 2023Accurate Differential Operators for Hybrid Neural Fieldscited by 9
  17. 2023Learned Alternating Minimization Algorithm for Dual-domain Sparse-View CT Reconstructioncited by 6
  18. 2023MEPNet: A Model-Driven Equivariant Proximal Network for Joint Sparse-View Reconstruction and Metal Artifact Reduction in CT Imagescited by 6
  19. 2023Hyb-NeRF: A Multiresolution Hybrid Encoding for Neural Radiance Fieldscited by 6
  20. 20233D Teeth Reconstruction from Panoramic Radiographs using Neural Implicit Functionscited by 6
  21. 2022Computed tomography coronary angiogram images, annotations and associated data of normal and diseased arteriescited by 4
  22. 2022Patch-wise Deep Metric Learning for Unsupervised Low-Dose CT Denoisingcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 4; 2026: 15.

25 papers.

Sort:

By area:

  1. 2024R2-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstructioncited by 67
  2. 2024EndoGS: Deformable Endoscopic Tissues Reconstruction with Gaussian Splattingcited by 33
  3. 2024EndoSparse: Real-Time Sparse View Synthesis of Endoscopic Scenes using Gaussian Splattingcited by 16
  4. 20243DGR-CAR: Coronary artery reconstruction from ultra-sparse 2D X-ray views with a 3D Gaussians representationcited by 7
  5. 2024Discretized Gaussian Representation for Tomographic Reconstructioncited by 6
  6. 2025X-GRM: Large Gaussian Reconstruction Model for Sparse-view X-rays to Computed Tomographycited by 6
  7. 20244DRGS: 4D Radiative Gaussian Splatting for Efficient 3D Vessel Reconstruction from Sparse-View Dynamic DSA Imagescited by 4
  8. 2025X-Field: A Physically Grounded Representation for 3D X-ray Reconstructioncited by 3
  9. 2026Active View Selection with Perturbed Gaussian Ensemble for Tomographic Reconstructioncited by 2
  10. 2025Cross-Distribution Diffusion Priors-Driven Iterative Reconstruction for Sparse-View CTcited by 1
  11. 2026M-Gaussian: An Magnetic Gaussian Framework for Efficient Multi-Stack MRI Reconstructioncited by 1
  12. 2026Spatiotemporal Gaussian representation-based dynamic reconstruction and motion estimation framework for time-resolved volumetric MR imaging (DREME-GSMR)cited by 1
13 more
  1. 2026DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstructioncited by 1
  2. 2026LINGO: Latent Initialization and Gradient Optimization for Sparse-view X-ray Novel View Synthesis and CT Reconstruction with 3D Gaussian Splattingcited by 1
  3. 2026SpectralCTGaussians: Projection-Domain Reconstruction and Basis Material Decomposition for Spectral CT using 3D Gaussian Splattingcited by 1
  4. 2025Medical Scene Reconstruction and Segmentation based on 3D Gaussian Representationcited by 0
  5. 2026Self-Supervised Slice-to-Volume Reconstruction with Gaussian Representations for Fetal MRIcited by 0
  6. 2026NAB: Neural Adaptive Binning for Sparse-View CT reconstructioncited by 0
  7. 2026Residual Gaussian Splatting for Ultra Sparse-View CBCT Reconstructioncited by 0
  8. 2026CD-RCM: Generalizable Continuous-Depth Novel View Synthesis for Reflectance Confocal Microscopycited by 0
  9. 2026Quantum CT via Dynamic Interval Encoding and Prior-Balanced QUBO Reconstructioncited by 0
  10. 2026X-Splat: Gaussian Splatting for 3D CBCT Generation from Single Panoramic Radiographcited by 0
  11. 2026Feed-Forward Hierarchical Gaussian Diffusion for Extreme CT Reconstructioncited by 0
  12. 2026Shared-Structure 4D Spectral Gaussian Representation for Sparse-View Spectral CT Reconstructioncited by 0
  13. 2026RePrior: Measurement-Reconciled Prior Correction for Sparse-View CBCT Reconstructioncited by 0