mlsanityData to 14 Oct 2026

X-GRM: Large Gaussian Reconstruction Model for Sparse-view X-rays to Computed Tomography

arXiv 2505.15235 ↗First posted 21 May 2025eess.IV cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Computed Tomography serves as an indispensable tool in clinical workflows, providing non-invasive visualization of internal anatomical structures. Existing CT reconstruction works are limited to small-capacity model architecture and inflexible volume representation. In this work, we present X-GRM (X-ray Gaussian Reconstruction Model), a large feedforward model for reconstructing 3D CT volumes from sparse-view 2D X-ray projections. X-GRM employs a scalable transformer-based architecture to encode sparse-view X-ray inputs, where tokens from different views are integrated efficiently. Then, these tokens are decoded into a novel volume representation, named Voxel-based Gaussian Splatting (VoxGS), which enables efficient CT volume extraction and differentiable X-ray rendering. This combination of a high-capacity model and flexible volume representation, empowers our model to produce high-quality reconstructions from various testing inputs, including in-domain and out-domain X-ray projections. Our codes are available at: https://github.com/CUHK-AIM-Group/X-GRM.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 55 of its 77 references that are in the map. First posted on arXiv 21 May 2025.

Builds on

55 of 77 references.

References · 55

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  5. 2022Scalable Diffusion Models with Transformerscited by 6,054
  6. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  7. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  8. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  9. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  10. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  11. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
  12. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,319
38 more
  1. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  2. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  3. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 774
  4. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 684
  5. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 651
  6. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 566
  7. 2025Continuous 3D Perception Model with Persistent Statecited by 548
  8. 2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 433
  9. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 378
  10. 2025Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Passcited by 367
  11. 2022AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentationcited by 351
  12. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 349
  13. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 301
  14. 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 248
  15. 2024TripoSR: Fast 3D Object Reconstruction from a Single Imagecited by 232
  16. 2016Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challengecited by 201
  17. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 180
  18. 2023PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Predictioncited by 165
  19. 2021NeRP: Implicit Neural Representation Learning with Prior Embedding for Sparsely Sampled Image Reconstructioncited by 146
  20. 2024MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Secondscited by 141
  21. 2024MeshLRM: Large Reconstruction Model for High-Quality Meshescited by 139
  22. 2022Solving 3D Inverse Problems using Pre-trained 2D Diffusion Modelscited by 132
  23. 2023Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problemscited by 132
  24. 2019PQ-NET: A Generative Part Seq2Seq Network for 3D Shapescited by 119
  25. 2022NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstructioncited by 108
  26. 2024FreeSplat: Generalizable 3D Gaussian Splatting Towards Free-View Synthesis of Indoor Scenescited by 89
  27. 2023Structure-Aware Sparse-View X-ray 3D Reconstructioncited by 72
  28. 2024R2-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstructioncited by 67
  29. 2024AbdomenAtlas: A Large-Scale, Detailed-Annotated, & Multi-Center Dataset for Efficient Transfer Learning and Open Algorithmic Benchmarkingcited by 65
  30. 2024Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesiscited by 58
  31. 2024HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstructioncited by 57
  32. 2023Improving 3D Imaging with Pre-Trained Perpendicular 2D Diffusion Modelscited by 53
  33. 2023Learning Deep Intensity Field for Extremely Sparse-View CBCT Reconstructioncited by 42
  34. 2024Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstructioncited by 32
  35. 2017Lose The Views: Limited Angle CT Reconstruction via Implicit Sinogram Completioncited by 31
  36. 20233DGR-CT: Sparse-View CT Reconstruction with a 3D Gaussian Representationcited by 25
  37. 2024DDGS-CT: Direction-Disentangled Gaussian Splatting for Realistic Volume Renderingcited by 23
  38. 2023FreeSeed: Frequency-band-aware and Self-guided Network for Sparse-view CT Reconstructioncited by 21

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 3.

6 papers.

  1. 2025VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detectioncited by 13
  2. 2025InnerGS: Internal Scenes Reconstruction and Segmentation via Factorized 3D Gaussian Splattingcited by 3
  3. 2025Cross-Distribution Diffusion Priors-Driven Iterative Reconstruction for Sparse-View CTcited by 1
  4. 2026SpectralCTGaussians: Projection-Domain Reconstruction and Basis Material Decomposition for Spectral CT using 3D Gaussian Splattingcited by 1
  5. 2026ILV: Iterative Latent Volumes for Fast and Accurate Sparse-View CT Reconstructioncited by 0
  6. 2026RePrior: Measurement-Reconciled Prior Correction for Sparse-View CBCT Reconstructioncited by 0