# Distributed Tomographic Reconstruction with Quantization

arXiv: https://arxiv.org/abs/2410.06106 · HTML: https://mlsanity.com/paper/2410.06106/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 43 references that are in the map.
- First posted on arXiv 8 Oct 2024.

## Builds on (most cited first, 7 of 7)

- [Scalable Plug-and-Play ADMM with Convergence Guarantees](https://mlsanity.com/paper/2006.03224/) (2020)
- [Joint ptycho-tomography with deep generative priors](https://mlsanity.com/paper/2009.09498/) (2020)
- [Federated Momentum Contrastive Clustering](https://mlsanity.com/paper/2206.05093/) (2022)
- [Petascale XCT: 3D Image Reconstruction with Hierarchical Communications on Multi-GPU Nodes](https://mlsanity.com/paper/2009.07226/) (2020)
- [Distributed Iterative CT Reconstruction using Multi-Agent Consensus Equilibrium](https://mlsanity.com/paper/1911.09278/) (2019)
- [CodEx: A Modular Framework for Joint Temporal De-blurring and Tomographic Reconstruction](https://mlsanity.com/paper/2111.06069/) (2021)
- [Distributed optimization for nonrigid nano-tomography](https://mlsanity.com/paper/2008.03375/) (2020)

## Abstract (arXiv)

Conventional tomographic reconstruction typically depends on centralized servers for both data storage and computation, leading to concerns about memory limitations and data privacy. Distributed reconstruction algorithms mitigate these issues by partitioning data across multiple nodes, reducing server load and enhancing privacy. However, these algorithms often encounter challenges related to memory constraints and communication overhead between nodes. In this paper, we introduce a decentralized Alternating Directions Method of Multipliers (ADMM) with configurable quantization. By distributing local objectives across nodes, our approach is highly scalable and can efficiently reconstruct images while adapting to available resources. To overcome communication bottlenecks, we propose two quantization techniques based on K-means clustering and JPEG compression. Numerical experiments with benchmark images illustrate the tradeoffs between communication efficiency, memory use, and reconstruction accuracy.