# Differentiable Forward Projector for X-ray Computed Tomography

arXiv: https://arxiv.org/abs/2307.05801 · HTML: https://mlsanity.com/paper/2307.05801/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 27 references that are in the map.
- First posted on arXiv 11 Jul 2023.

## Builds on (most cited first, 10 of 10)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Framing U-Net via Deep Convolutional Framelets: Application to Sparse-view CT](https://mlsanity.com/paper/1708.08333/) (2017)
- [CNN-Based Projected Gradient Descent for Consistent Image Reconstruction](https://mlsanity.com/paper/1709.01809/) (2017)
- [DOLCE: A Model-Based Probabilistic Diffusion Framework for Limited-Angle CT Reconstruction](https://mlsanity.com/paper/2211.12340/) (2022)
- [Lose The Views: Limited Angle CT Reconstruction via Implicit Sinogram Completion](https://mlsanity.com/paper/1711.10388/) (2017)
- [Sparse-view Cone Beam CT Reconstruction using Data-consistent Supervised and Adversarial Learning from Scarce Training Data](https://mlsanity.com/paper/2201.09318/) (2022)
- [Diffraction tomography with a deep image prior](https://mlsanity.com/paper/1912.05330/) (2019)
- [Extreme Few-view CT Reconstruction using Deep Inference](https://mlsanity.com/paper/1910.05375/) (2019)
- [LRIP-Net: Low-Resolution Image Prior based Network for Limited-Angle CT Reconstruction](https://mlsanity.com/paper/2208.00207/) (2022)
- [Improving Limited Angle CT Reconstruction with a Robust GAN Prior](https://mlsanity.com/paper/1910.01634/) (2019)

## Built on by (most cited first, 14 of 14)

- [CT Reconstruction using Diffusion Posterior Sampling conditioned on a Nonlinear Measurement Model](https://mlsanity.com/paper/2312.01464/) (2023)
- [DM4CT: Benchmarking Diffusion Models for Computed Tomography Reconstruction](https://mlsanity.com/paper/2602.18589/) (2026)
- [Distributed Stochastic Optimization of a Neural Representation Network for Time-Space Tomography Reconstruction](https://mlsanity.com/paper/2404.19075/) (2024)
- [Neural rendering enables dynamic tomography](https://mlsanity.com/paper/2410.20558/) (2024)
- [Virtual-mask Informed Prior for Sparse-view Dual-Energy CT Reconstruction](https://mlsanity.com/paper/2504.07753/) (2025)
- [Limited-Angle CBCT Reconstruction via Geometry-Integrated Cycle-domain Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2506.13545/) (2025)
- [Cross-Distribution Diffusion Priors-Driven Iterative Reconstruction for Sparse-View CT](https://mlsanity.com/paper/2509.13576/) (2025)
- [Sequential-Scanning Dual-Energy CT Imaging Using High Temporal Resolution Image Reconstruction and Error-Compensated Material Basis Image Generation](https://mlsanity.com/paper/2408.14754/) (2024)
- [Pseudoinverse Diffusion Models for Generative CT Image Reconstruction from Low Dose Data](https://mlsanity.com/paper/2502.15064/) (2025)
- [Tada-DIP: Input-adaptive Deep Image Prior for One-shot 3D Image Reconstruction](https://mlsanity.com/paper/2512.03962/) (2025)
- [Efficient Noise Context-Aware Representation for Low-Dose CT Denoising](https://mlsanity.com/paper/2608.10343/) (2026)
- [Splat-based Metal Artifact Reduction in Cone-Beam CT via Polychromatic Modeling](https://mlsanity.com/paper/2608.13159/) (2026)
- [Toward a Foundation Plug-and-Play Prior for Computed Tomography Reconstruction via a Multimodal Diffusion Model](https://mlsanity.com/paper/2608.23190/) (2026)
- [Plug-and-Play Methods Provably Converge Even with Improperly Trained Denoisers: Convergence by Architectural Design](https://mlsanity.com/paper/2609.33087/) (2026)

## Abstract (arXiv)

Data-driven deep learning has been successfully applied to various computed tomographic reconstruction problems. The deep inference models may outperform existing analytical and iterative algorithms, especially in ill-posed CT reconstruction. However, those methods often predict images that do not agree with the measured projection data. This paper presents an accurate differentiable forward and back projection software library to ensure the consistency between the predicted images and the original measurements. The software library efficiently supports various projection geometry types while minimizing the GPU memory footprint requirement, which facilitates seamless integration with existing deep learning training and inference pipelines. The proposed software is available as open source: https://github.com/LLNL/LEAP.