mlsanityData to 14 Oct 2026

X-LRM: X-ray Large Reconstruction Model for Extremely Sparse-View Computed Tomography Recovery in One Second

arXiv 2503.06382 ↗First posted 9 Mar 2025eess.IV cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Sparse-view 3D CT reconstruction aims to recover volumetric structures from a limited number of 2D X-ray projections. Existing feedforward methods are constrained by the scarcity of large-scale training datasets and the absence of direct and consistent 3D representations. In this paper, we propose an X-ray Large Reconstruction Model (X-LRM) for extremely sparse-view (<10 views) CT reconstruction. X-LRM consists of two key components: X-former and X-triplane. X-former can handle an arbitrary number of input views using an MLP-based image tokenizer and a Transformer-based encoder. The output tokens are then upsampled into our X-triplane representation, which models the 3D radiodensity as an implicit neural field. To support the training of X-LRM, we introduce Torso-16K, a large-scale dataset comprising over 16K volume-projection pairs of various torso organs. Extensive experiments demonstrate that X-LRM outperforms the state-of-the-art method by 1.5 dB and achieves 27× faster speed with better flexibility. Furthermore, the evaluation of lung segmentation tasks also suggests the practical value of our approach. Our code and dataset will be released at https://github.com/Richard-Guofeng-Zhang/X-LRM

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 39 of its 69 references that are in the map. First posted on arXiv 9 Mar 2025.

Builds on

39 of 69 references.

References · 39

  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. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  6. 2016Layer Normalizationcited by 5,669
  7. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  8. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  9. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  10. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  11. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 774
  12. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 651
27 more
  1. 2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 433
  2. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 378
  3. 2022AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentationcited by 351
  4. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 349
  5. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 333
  6. 2024TripoSR: Fast 3D Object Reconstruction from a Single Imagecited by 232
  7. 2016Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challengecited by 201
  8. 2023PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Predictioncited by 165
  9. 2021NeRP: Implicit Neural Representation Learning with Prior Embedding for Sparsely Sampled Image Reconstructioncited by 146
  10. 2024MeshLRM: Large Reconstruction Model for High-Quality Meshescited by 139
  11. 2022Solving 3D Inverse Problems using Pre-trained 2D Diffusion Modelscited by 132
  12. 2023Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problemscited by 132
  13. 2019PQ-NET: A Generative Part Seq2Seq Network for 3D Shapescited by 119
  14. 2022NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstructioncited by 108
  15. 2023Structure-Aware Sparse-View X-ray 3D Reconstructioncited by 72
  16. 2024R2-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstructioncited by 67
  17. 2024AbdomenAtlas: A Large-Scale, Detailed-Annotated, & Multi-Center Dataset for Efficient Transfer Learning and Open Algorithmic Benchmarkingcited by 65
  18. 2024Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesiscited by 58
  19. 2023Improving 3D Imaging with Pre-Trained Perpendicular 2D Diffusion Modelscited by 53
  20. 2023Learning Deep Intensity Field for Extremely Sparse-View CBCT Reconstructioncited by 42
  21. 2024Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstructioncited by 32
  22. 2017Lose The Views: Limited Angle CT Reconstruction via Implicit Sinogram Completioncited by 31
  23. 2023FreeSeed: Frequency-band-aware and Self-guided Network for Sparse-view CT Reconstructioncited by 21
  24. 2024Learning 3D Gaussians for Extremely Sparse-View Cone-Beam CT Reconstructioncited by 18
  25. 2024C^2RV: Cross-Regional and Cross-View Learning for Sparse-View CBCT Reconstructioncited by 15
  26. 2024Deep Rib Fracture Instance Segmentation and Classification from CT on the RibFrac Challengecited by 14
  27. 2024LucidFusion: Reconstructing 3D Gaussians with Arbitrary Unposed Imagescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2025X-GRM: Large Gaussian Reconstruction Model for Sparse-view X-rays to Computed Tomographycited by 6
  2. 2025Are Pixel-Wise Metrics Reliable for Sparse-View Computed Tomography Reconstruction?cited by 6
  3. 2026Active View Selection with Perturbed Gaussian Ensemble for Tomographic Reconstructioncited by 2
  4. 2026DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstructioncited 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