# SNAF: Sparse-view CBCT Reconstruction with Neural Attenuation Fields

arXiv: https://arxiv.org/abs/2211.17048 · HTML: https://mlsanity.com/paper/2211.17048/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 24 references that are in the map.
- First posted on arXiv 30 Nov 2022.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [Depth-supervised NeRF: Fewer Views and Faster Training for Free](https://mlsanity.com/paper/2107.02791/) (2021)
- [RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs](https://mlsanity.com/paper/2112.00724/) (2021)
- [Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis](https://mlsanity.com/paper/2104.00677/) (2021)
- [Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenes](https://mlsanity.com/paper/2104.06935/) (2021)
- [HumanNeRF: Efficiently Generated Human Radiance Field from Sparse Inputs](https://mlsanity.com/paper/2112.02789/) (2021)
- [NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction](https://mlsanity.com/paper/2209.14540/) (2022)
- [Pose-Aware Instance Segmentation Framework from Cone Beam CT Images for Tooth Segmentation](https://mlsanity.com/paper/2002.02143/) (2020)

## Built on by (most cited first, 23 of 23)

- [Implicit Neural Representation in Medical Imaging: A Comparative Survey](https://mlsanity.com/paper/2307.16142/) (2023)
- [Learning Deep Intensity Field for Extremely Sparse-View CBCT Reconstruction](https://mlsanity.com/paper/2303.06681/) (2023)
- [C^2RV: Cross-Regional and Cross-View Learning for Sparse-View CBCT Reconstruction](https://mlsanity.com/paper/2406.03902/) (2024)
- [Geometry-Aware Attenuation Learning for Sparse-View CBCT Reconstruction](https://mlsanity.com/paper/2303.14739/) (2023)
- [Neural Radiance Fields in Medical Imaging: A Survey](https://mlsanity.com/paper/2402.17797/) (2024)
- [3DGR-CAR: Coronary artery reconstruction from ultra-sparse 2D X-ray views with a 3D Gaussians representation](https://mlsanity.com/paper/2410.00404/) (2024)
- [TiAVox: Time-aware Attenuation Voxels for Sparse-view 4D DSA Reconstruction](https://mlsanity.com/paper/2309.02318/) (2023)
- [3D Vessel Reconstruction from Sparse-View Dynamic DSA Images via Vessel Probability Guided Attenuation Learning](https://mlsanity.com/paper/2405.10705/) (2024)
- [DeepSparse: A Foundation Model for Sparse-View CBCT Reconstruction](https://mlsanity.com/paper/2505.02628/) (2025)
- [NeRF-CA: Dynamic Reconstruction of X-ray Coronary Angiography with Extremely Sparse-views](https://mlsanity.com/paper/2408.16355/) (2024)
- [4DRGS: 4D Radiative Gaussian Splatting for Efficient 3D Vessel Reconstruction from Sparse-View Dynamic DSA Images](https://mlsanity.com/paper/2412.12919/) (2024)
- [ZS-SRT: An Efficient Zero-Shot Super-Resolution Training Method for Neural Radiance Fields](https://mlsanity.com/paper/2312.12122/) (2023)
- [Modeling the Neonatal Brain Development Using Implicit Neural Representations](https://mlsanity.com/paper/2408.08647/) (2024)
- [NeAS: 3D Reconstruction from X-ray Images using Neural Attenuation Surface](https://mlsanity.com/paper/2503.07491/) (2025)
- [ViT-NeBLa: A Hybrid Vision Transformer and Neural Beer-Lambert Framework for Single-View 3D Reconstruction of Oral Anatomy from Panoramic Radiographs](https://mlsanity.com/paper/2506.13195/) (2025)
- [Intensity Field Decomposition for Tissue-Guided Neural Tomography](https://mlsanity.com/paper/2411.00900/) (2024)
- [Epi-NAF: Enhancing Neural Attenuation Fields for Limited-Angle CT with Epipolar Consistency Conditions](https://mlsanity.com/paper/2411.06181/) (2024)
- [Trans2-CBCT: A Dual-Transformer Framework for Sparse-View CBCT Reconstruction](https://mlsanity.com/paper/2506.17425/) (2025)
- [X2BR: High-Fidelity 3D Bone Reconstruction from a Planar X-Ray Image with Hybrid Neural Implicit Methods](https://mlsanity.com/paper/2504.08675/) (2025)
- [Iterative Diffusion-Refined Neural Attenuation Fields for Multi-Source Stationary CT Reconstruction: NAF Meets Diffusion Model](https://mlsanity.com/paper/2511.14310/) (2025)
- [Continuity-driven Synergistic Diffusion with Neural Priors for Ultra-Sparse-View CBCT Reconstruction](https://mlsanity.com/paper/2602.07980/) (2026)
- [Conditional Diffusion Posterior Alignment for Sparse-View CT Reconstruction](https://mlsanity.com/paper/2604.21960/) (2026)
- [K-U-KAN: Koopman-Enhanced U-KAN for 3D Dental Reconstruction from a Single Panoramic X-ray Radiograph](https://mlsanity.com/paper/2605.25163/) (2026)

## Abstract (arXiv)

Cone beam computed tomography (CBCT) has been widely used in clinical practice, especially in dental clinics, while the radiation dose of X-rays when capturing has been a long concern in CBCT imaging. Several research works have been proposed to reconstruct high-quality CBCT images from sparse-view 2D projections, but the current state-of-the-arts suffer from artifacts and the lack of fine details. In this paper, we propose SNAF for sparse-view CBCT reconstruction by learning the neural attenuation fields, where we have invented a novel view augmentation strategy to overcome the challenges introduced by insufficient data from sparse input views. Our approach achieves superior performance in terms of high reconstruction quality (30+ PSNR) with only 20 input views (25 times fewer than clinical collections), which outperforms the state-of-the-arts. We have further conducted comprehensive experiments and ablation analysis to validate the effectiveness of our approach.