# Swap-Net: A Memory-Efficient 2.5D Network for Sparse-View 3D Cone Beam CT Reconstruction

arXiv: https://arxiv.org/abs/2410.10836 · HTML: https://mlsanity.com/paper/2410.10836/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 80 references that are in the map.
- First posted on arXiv 29 Sep 2024.

## Builds on (most cited first, 30 of 30)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [Deep Convolutional Neural Network for Inverse Problems in Imaging](https://mlsanity.com/paper/1611.03679/) (2016)
- [Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing](https://mlsanity.com/paper/1912.10557/) (2019)
- [MoDL: Model Based Deep Learning Architecture for Inverse Problems](https://mlsanity.com/paper/1712.02862/) (2017)
- [Learned Primal-dual Reconstruction](https://mlsanity.com/paper/1707.06474/) (2017)
- [Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)](https://mlsanity.com/paper/1702.00288/) (2017)
- [Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures](https://mlsanity.com/paper/1409.2574/) (2014)
- [CNN-Based Projected Gradient Descent for Consistent Image Reconstruction](https://mlsanity.com/paper/1709.01809/) (2017)
- [Image Reconstruction: From Sparsity to Data-adaptive Methods and Machine Learning](https://mlsanity.com/paper/1904.02816/) (2019)
- [Improving 3D Imaging with Pre-Trained Perpendicular 2D Diffusion Models](https://mlsanity.com/paper/2303.08440/) (2023)
- [Model based learning for accelerated, limited-view 3D photoacoustic tomography](https://mlsanity.com/paper/1708.09832/) (2017)
- [SUNet: Swin Transformer UNet for Image Denoising](https://mlsanity.com/paper/2202.14009/) (2022)
- [Momentum-Net: Fast and convergent iterative neural network for inverse problems](https://mlsanity.com/paper/1907.11818/) (2019)
- [End-to-end reconstruction meets data-driven regularization for inverse problems](https://mlsanity.com/paper/2106.03538/) (2021)
- [Lose The Views: Limited Angle CT Reconstruction via Implicit Sinogram Completion](https://mlsanity.com/paper/1711.10388/) (2017)
- [Online Deep Equilibrium Learning for Regularization by Denoising](https://mlsanity.com/paper/2205.13051/) (2022)
- [A Cone-Beam X-Ray CT Data Collection designed for Machine Learning](https://mlsanity.com/paper/1905.04787/) (2019)
- [SGD-Net: Efficient Model-Based Deep Learning with Theoretical Guarantees](https://mlsanity.com/paper/2101.09379/) (2021)
- [Sparse-view Cone Beam CT Reconstruction using Data-consistent Supervised and Adversarial Learning from Scarce Training Data](https://mlsanity.com/paper/2201.09318/) (2022)
- [PWLS-ULTRA: An Efficient Clustering and Learning-Based Approach for Low-Dose 3D CT Image Reconstruction](https://mlsanity.com/paper/1703.09165/) (2017)
- [Data Consistent Artifact Reduction for Limited Angle Tomography with Deep Learning Prior](https://mlsanity.com/paper/1908.06792/) (2019)
- [Limited View and Sparse Photoacoustic Tomography for Neuroimaging with Deep Learning](https://mlsanity.com/paper/1911.04357/) (2019)
- [2.5D Deep Learning for CT Image Reconstruction using a Multi-GPU implementation](https://mlsanity.com/paper/1812.08367/) (2018)
- [Extreme Few-view CT Reconstruction using Deep Inference](https://mlsanity.com/paper/1910.05375/) (2019)
- [Local Models for Scatter Estimation and Descattering in Polyenergetic X-Ray Tomography](https://mlsanity.com/paper/2012.06348/) (2020)
- [3D helical CT Reconstruction with a Memory Efficient Learned Primal-Dual Architecture](https://mlsanity.com/paper/2205.11952/) (2022)
- [4D X-Ray CT Reconstruction using Multi-Slice Fusion](https://mlsanity.com/paper/1906.06601/) (2019)
- [Deep Learning Reconstruction for 9-View Dual Energy CT Baggage Scanner](https://mlsanity.com/paper/1801.01258/) (2018)

## Built on by (most cited first, 3 of 3)

- [Learning robust parameter inference and density reconstruction in flyer plate impact experiments](https://mlsanity.com/paper/2506.23914/) (2025)
- [Clinical Metadata Guided Limited-Angle CT Image Reconstruction](https://mlsanity.com/paper/2509.01752/) (2025)
- [Material Identification using Multi-Modal Intrinsic Radiation and Radiography](https://mlsanity.com/paper/2603.27036/) (2026)

## Abstract (arXiv)

Reconstructing 3D cone beam computed tomography (CBCT) images from a limited set of projections is an important inverse problem in many imaging applications from medicine to inertial confinement fusion (ICF). The performance of traditional methods such as filtered back projection (FBP) and model-based regularization is sub-optimal when the number of available projections is limited. In the past decade, deep learning (DL) has gained great popularity for solving CT inverse problems. A typical DL-based method for CBCT image reconstruction is to learn an end-to-end mapping by training a 2D or 3D network. However, 2D networks fail to fully use global information. While 3D networks are desirable, they become impractical as image sizes increase because of the high memory cost. This paper proposes Swap-Net, a memory-efficient 2.5D network for sparse-view 3D CBCT image reconstruction. Swap-Net uses a sequence of novel axes-swapping operations to produce 3D volume reconstruction in an end-to-end fashion without using full 3D convolutions. Simulation results show that Swap-Net consistently outperforms baseline methods both quantitatively and qualitatively in terms of reducing artifacts and preserving details of complex hydrodynamic simulations of relevance to the ICF community.