# TiAVox: Time-aware Attenuation Voxels for Sparse-view 4D DSA Reconstruction

arXiv: https://arxiv.org/abs/2309.02318 · HTML: https://mlsanity.com/paper/2309.02318/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 44 references that are in the map.
- First posted on arXiv 5 Sep 2023.

## Builds on (most cited first, 30 of 34)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [D-NeRF: Neural Radiance Fields for Dynamic Scenes](https://mlsanity.com/paper/2011.13961/) (2020)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://mlsanity.com/paper/2111.11215/) (2021)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [K-Planes: Explicit Radiance Fields in Space, Time, and Appearance](https://mlsanity.com/paper/2301.10241/) (2023)
- [RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs](https://mlsanity.com/paper/2112.00724/) (2021)
- [HexPlane: A Fast Representation for Dynamic Scenes](https://mlsanity.com/paper/2301.09632/) (2023)
- [Deep Convolutional Neural Network for Inverse Problems in Imaging](https://mlsanity.com/paper/1611.03679/) (2016)
- [Fast Dynamic Radiance Fields with Time-Aware Neural Voxels](https://mlsanity.com/paper/2205.15285/) (2022)
- [Image reconstruction by domain transform manifold learning](https://mlsanity.com/paper/1704.08841/) (2017)
- [Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Rendering](https://mlsanity.com/paper/2211.11610/) (2022)
- [NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fields](https://mlsanity.com/paper/2210.15947/) (2022)
- [NeRP: Implicit Neural Representation Learning with Prior Embedding for Sparsely Sampled Image Reconstruction](https://mlsanity.com/paper/2108.10991/) (2021)
- [Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2307.11335/) (2023)
- [Neural Rendering for Stereo 3D Reconstruction of Deformable Tissues in Robotic Surgery](https://mlsanity.com/paper/2206.15255/) (2022)
- [NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction](https://mlsanity.com/paper/2209.14540/) (2022)
- [Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction](https://mlsanity.com/paper/2208.12697/) (2022)
- [Framing U-Net via Deep Convolutional Framelets: Application to Sparse-view CT](https://mlsanity.com/paper/1708.08333/) (2017)
- [Dynamic CT Reconstruction from Limited Views with Implicit Neural Representations and Parametric Motion Fields](https://mlsanity.com/paper/2104.11745/) (2021)
- [Temporal Interpolation Is All You Need for Dynamic Neural Radiance Fields](https://mlsanity.com/paper/2302.09311/) (2023)
- [Neural Surface Reconstruction of Dynamic Scenes with Monocular RGB-D Camera](https://mlsanity.com/paper/2206.15258/) (2022)
- [3D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning from a 2D Trained Network](https://mlsanity.com/paper/1802.05656/) (2018)
- [Neural LerPlane Representations for Fast 4D Reconstruction of Deformable Tissues](https://mlsanity.com/paper/2305.19906/) (2023)
- [ViP-NeRF: Visibility Prior for Sparse Input Neural Radiance Fields](https://mlsanity.com/paper/2305.00041/) (2023)
- [Learning Deep Intensity Field for Extremely Sparse-View CBCT Reconstruction](https://mlsanity.com/paper/2303.06681/) (2023)
- [Self-Supervised Coordinate Projection Network for Sparse-View Computed Tomography](https://mlsanity.com/paper/2209.05483/) (2022)

## Built on by (most cited first, 5 of 5)

- [Efficient Deformable Tissue Reconstruction via Orthogonal Neural Plane](https://mlsanity.com/paper/2312.15253/) (2023)
- [TOGS: Gaussian Splatting with Temporal Opacity Offset for Real-Time 4D DSA Rendering](https://mlsanity.com/paper/2403.19586/) (2024)
- [3D Vessel Reconstruction from Sparse-View Dynamic DSA Images via Vessel Probability Guided Attenuation Learning](https://mlsanity.com/paper/2405.10705/) (2024)
- [NeRF-CA: Dynamic Reconstruction of X-ray Coronary Angiography with Extremely Sparse-views](https://mlsanity.com/paper/2408.16355/) (2024)
- [Segmentation-Driven Initialization for Sparse-view 3D Gaussian Splatting](https://mlsanity.com/paper/2509.11853/) (2025)

## Abstract (arXiv)

Four-dimensional Digital Subtraction Angiography (4D DSA) plays a critical role in the diagnosis of many medical diseases, such as Arteriovenous Malformations (AVM) and Arteriovenous Fistulas (AVF). Despite its significant application value, the reconstruction of 4D DSA demands numerous views to effectively model the intricate vessels and radiocontrast flow, thereby implying a significant radiation dose. To address this high radiation issue, we propose a Time-aware Attenuation Voxel (TiAVox) approach for sparse-view 4D DSA reconstruction, which paves the way for high-quality 4D imaging. Additionally, 2D and 3D DSA imaging results can be generated from the reconstructed 4D DSA images. TiAVox introduces 4D attenuation voxel grids, which reflect attenuation properties from both spatial and temporal dimensions. It is optimized by minimizing discrepancies between the rendered images and sparse 2D DSA images. Without any neural network involved, TiAVox enjoys specific physical interpretability. The parameters of each learnable voxel represent the attenuation coefficients. We validated the TiAVox approach on both clinical and simulated datasets, achieving a 31.23 Peak Signal-to-Noise Ratio (PSNR) for novel view synthesis using only 30 views on the clinically sourced dataset, whereas traditional Feldkamp-Davis-Kress methods required 133 views. Similarly, with merely 10 views from the synthetic dataset, TiAVox yielded a PSNR of 34.32 for novel view synthesis and 41.40 for 3D reconstruction. We also executed ablation studies to corroborate the essential components of TiAVox. The code will be publically available.