# Trans2-CBCT: A Dual-Transformer Framework for Sparse-View CBCT Reconstruction

arXiv: https://arxiv.org/abs/2506.17425 · HTML: https://mlsanity.com/paper/2506.17425/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 43 references that are in the map.
- First posted on arXiv 20 Jun 2025.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images](https://mlsanity.com/paper/2201.01266/) (2022)
- [Deep Convolutional Neural Network for Inverse Problems in Imaging](https://mlsanity.com/paper/1611.03679/) (2016)
- [BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models](https://mlsanity.com/paper/2205.07680/) (2022)
- [Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challenge](https://mlsanity.com/paper/1612.08012/) (2016)
- [NeRP: Implicit Neural Representation Learning with Prior Embedding for Sparsely Sampled Image Reconstruction](https://mlsanity.com/paper/2108.10991/) (2021)
- [NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction](https://mlsanity.com/paper/2209.14540/) (2022)
- [TransMed: Transformers Advance Multi-modal Medical Image Classification](https://mlsanity.com/paper/2103.05940/) (2021)
- [R2-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction](https://mlsanity.com/paper/2405.20693/) (2024)
- [Learning Deep Intensity Field for Extremely Sparse-View CBCT Reconstruction](https://mlsanity.com/paper/2303.06681/) (2023)
- [A Robust Volumetric Transformer for Accurate 3D Tumor Segmentation](https://mlsanity.com/paper/2111.13300/) (2021)
- [D-Former: A U-shaped Dilated Transformer for 3D Medical Image Segmentation](https://mlsanity.com/paper/2201.00462/) (2022)
- [SNAF: Sparse-view CBCT Reconstruction with Neural Attenuation Fields](https://mlsanity.com/paper/2211.17048/) (2022)
- [FreeSeed: Frequency-band-aware and Self-guided Network for Sparse-view CT Reconstruction](https://mlsanity.com/paper/2307.05890/) (2023)
- [Learning 3D Gaussians for Extremely Sparse-View Cone-Beam CT Reconstruction](https://mlsanity.com/paper/2407.01090/) (2024)
- [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)
- [Deep Back Projection for Sparse-View CT Reconstruction](https://mlsanity.com/paper/1807.02370/) (2018)
- [Intensity Field Decomposition for Tissue-Guided Neural Tomography](https://mlsanity.com/paper/2411.00900/) (2024)

## Built on by (most cited first, 1 of 1)

- [DyG2T: Modeling Object Dynamics with 3D Gaussian Temporal-Spatial Particle Graph Transformer](https://mlsanity.com/paper/2608.18498/) (2026)

## Abstract (arXiv)

Cone-beam computed tomography (CBCT) using only a few X-ray projection views enables faster scans with lower radiation dose, but the resulting severe under-sampling causes strong artifacts and poor spatial coverage. We address these challenges in a unified framework. First, we replace conventional UNet/ResNet encoders with TransUNet, a hybrid CNN-Transformer model. Convolutional layers capture local details, while self-attention layers enhance global context. We adapt TransUNet to CBCT by combining multi-scale features, querying view-specific features per 3D point, and adding a lightweight attenuation-prediction head. This yields Trans-CBCT, which surpasses prior baselines by 1.17 dB PSNR and 0.0163 SSIM on the LUNA16 dataset with six views. Second, we introduce a neighbor-aware Point Transformer to enforce volumetric coherence. This module uses 3D positional encoding and attention over k-nearest neighbors to improve spatial consistency. The resulting model, Trans2-CBCT, provides an additional gain of 0.63 dB PSNR and 0.0117 SSIM. Experiments on LUNA16 and ToothFairy show consistent gains from six to ten views, validating the effectiveness of combining CNN-Transformer features with point-based geometry reasoning for sparse-view CBCT reconstruction.