mlsanityData to 7 Oct 2026

NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction

arXiv 2209.14540 ↗First posted 29 Sep 2022eess.IV cs.CVcited by 106

Not on the map. Why?

Abstract (arXiv)

This paper proposes a novel and fast self-supervised solution for sparse-view CBCT reconstruction (Cone Beam Computed Tomography) that requires no external training data. Specifically, the desired attenuation coefficients are represented as a continuous function of 3D spatial coordinates, parameterized by a fully-connected deep neural network. We synthesize projections discretely and train the network by minimizing the error between real and synthesized projections. A learning-based encoder entailing hash coding is adopted to help the network capture high-frequency details. This encoder outperforms the commonly used frequency-domain encoder in terms of having higher performance and efficiency, because it exploits the smoothness and sparsity of human organs. Experiments have been conducted on both human organ and phantom datasets. The proposed method achieves state-of-the-art accuracy and spends reasonably short computation time.

Key facts. Cited by 106 papers in the map (data through 7 Oct 2026). Builds on 12 of its 29 references that are in the map. First posted on arXiv 29 Sep 2022.

Builds on

12 of 29 references.

References · 12

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  3. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  4. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  5. 2018On the Spectral Bias of Neural Networkscited by 1,321
  6. 2017Learned Primal-dual Reconstructioncited by 251
  7. 2019X2CT-GAN: Reconstructing CT from Biplanar X-Rays with Generative Adversarial Networkscited by 85
  8. 2021IREM: High-Resolution Magnetic Resonance (MR) Image Reconstruction via Implicit Neural Representationcited by 42
  9. 2017Lose The Views: Limited Angle CT Reconstruction via Implicit Sinogram Completioncited by 31
  10. 2020End-To-End Convolutional Neural Network for 3D Reconstruction of Knee Bones From Bi-Planar X-Ray Imagescited by 28
  11. 2021Improving Generalizability in Limited-Angle CT Reconstruction with Sinogram Extrapolationcited by 8
  12. 2017LEARN: Learned Experts' Assessment-based Reconstruction Network for Sparse-data CTcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 14; 2024: 31; 2025: 24; 2026: 34.

106 papers.

Sort:

By area:

  1. 2023Structure-Aware Sparse-View X-ray 3D Reconstructioncited by 70
  2. 2024R2-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstructioncited by 65
  3. 2024Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesiscited by 56
  4. 2023Learning Deep Intensity Field for Extremely Sparse-View CBCT Reconstructioncited by 42
  5. 2022Neural Implicit k-Space for Binning-free Non-Cartesian Cardiac MR Imagingcited by 35
  6. 20233DGR-CT: Sparse-View CT Reconstruction with a 3D Gaussian Representationcited by 24
  7. 2022SNAF: Sparse-view CBCT Reconstruction with Neural Attenuation Fieldscited by 23
  8. 2024DDGS-CT: Direction-Disentangled Gaussian Splatting for Realistic Volume Renderingcited by 22
  9. 2024DPER: Diffusion Prior Driven Neural Representation for Limited Angle and Sparse View CT Reconstructioncited by 17
  10. 2024Learning 3D Gaussians for Extremely Sparse-View Cone-Beam CT Reconstructioncited by 16
  11. 2024C^2RV: Cross-Regional and Cross-View Learning for Sparse-View CBCT Reconstructioncited by 15
  12. 2023Geometry-Aware Attenuation Learning for Sparse-View CBCT Reconstructioncited by 12
38 more
  1. 2023How to Train Neural Field Representations: A Comprehensive Study and Benchmarkcited by 12
  2. 2024Volumetrically Consistent 3D Gaussian Rasterizationcited by 11
  3. 2025Fit Pixels, Get Labels: Meta-learned Implicit Networks for Image Segmentationcited by 11
  4. 2023Unsupervised Polychromatic Neural Representation for CT Metal Artifact Reductioncited by 9
  5. 2024Implicit Neural Representations for Robust Joint Sparse-View CT Reconstructioncited by 9
  6. 2023CT Reconstruction from Few Planar X-rays with Application towards Low-resource Radiotherapycited by 8
  7. 2024DIFR3CT: Latent Diffusion for Probabilistic 3D CT Reconstruction from Few Planar X-Rayscited by 8
  8. 2024Neural Radiance Fields in Medical Imaging: A Surveycited by 7
  9. 2024TOGS: Gaussian Splatting with Temporal Opacity Offset for Real-Time 4D DSA Renderingcited by 7
  10. 2024NeRF-US: Removing Ultrasound Imaging Artifacts from Neural Radiance Fields in the Wildcited by 7
  11. 20243DGR-CAR: Coronary artery reconstruction from ultra-sparse 2D X-ray views with a 3D Gaussians representationcited by 7
  12. 2024Glimpse: Generalized Locality for Scalable and Robust CTcited by 6
  13. 2024DeepCA: Deep Learning-based 3D Coronary Artery Tree Reconstruction from Two 2D Non-simultaneous X-ray Angiography Projectionscited by 6
  14. 2024Discretized Gaussian Representation for Tomographic Reconstructioncited by 6
  15. 2025MedFuncta: A Unified Framework for Learning Efficient Medical Neural Fieldscited by 6
  16. 2025X2-Gaussian: 4D Radiative Gaussian Splatting for Continuous-time Tomographic Reconstructioncited by 6
  17. 2025Are Pixel-Wise Metrics Reliable for Sparse-View Computed Tomography Reconstruction?cited by 6
  18. 2022Joint Rigid Motion Correction and Sparse-View CT via Self-Calibrating Neural Fieldcited by 5
  19. 2023TiAVox: Time-aware Attenuation Voxels for Sparse-view 4D DSA Reconstructioncited by 5
  20. 2023Continuous 3D Myocardial Motion Tracking via Echocardiographycited by 5
  21. 20243D Vessel Reconstruction from Sparse-View Dynamic DSA Images via Vessel Probability Guided Attenuation Learningcited by 5
  22. 2025X-LRM: X-ray Large Reconstruction Model for Extremely Sparse-View Computed Tomography Recovery in One Secondcited by 5
  23. 2025X-GRM: Large Gaussian Reconstruction Model for Sparse-view X-rays to Computed Tomographycited by 5
  24. 2025GR-Gaussian: Graph-Based Radiative Gaussian Splatting for Sparse-View CT Reconstructioncited by 5
  25. 2024NeRF-CA: Dynamic Reconstruction of X-ray Coronary Angiography with Extremely Sparse-viewscited by 4
  26. 2025DeepSparse: A Foundation Model for Sparse-View CBCT Reconstructioncited by 4
  27. 2023Oral-3Dv2: 3D Oral Reconstruction from Panoramic X-Ray Imaging with Implicit Neural Representationcited by 3
  28. 2023NeBLa: Neural Beer-Lambert for 3D Reconstruction of Oral Structures from Panoramic Radiographscited by 3
  29. 2023ZS-SRT: An Efficient Zero-Shot Super-Resolution Training Method for Neural Radiance Fieldscited by 3
  30. 2024Ray-driven Spectral CT Reconstruction Based on Neural Base-Material Fieldscited by 3
  31. 2024Metric-Guided Conformal Bounds for Probabilistic Image Reconstructioncited by 3
  32. 2024NeCA: 3D Coronary Artery Tree Reconstruction from Two 2D Projections via Neural Implicit Representationcited by 3
  33. 2024AC-IND: Sparse CT reconstruction based on attenuation coefficient estimation and implicit neural distributioncited by 3
  34. 2024Differentiable Voxel-based X-ray Rendering Improves Sparse-View 3D CBCT Reconstructioncited by 3
  35. 2024Unsupervised Multi-Parameter Inverse Solving for Reducing Ring Artifacts in 3D X-Ray CBCTcited by 3
  36. 20244DRGS: 4D Radiative Gaussian Splatting for Efficient 3D Vessel Reconstruction from Sparse-View Dynamic DSA Imagescited by 3
  37. 2025Unsupervised Self-Prior Embedding Neural Representation for Iterative Sparse-View CT Reconstructioncited by 3
  38. 2025NeAS: 3D Reconstruction from X-ray Images using Neural Attenuation Surfacecited by 3

50 most cited of 106 All 106 (JSON)