开源深度学习工具包，用于解决成像逆问题重建
DeepInverse: A Python package for solving imaging inverse problems with deep learning
- 基于PyTorch构建，涵盖正向算子到神经网络训练全流程
- 支持光学、MRI、断层扫描等多类成像逆问题求解
- 适合图像重建研究者快速搭建实验框架
DeepInverse 是一个基于 PyTorch 的开源库，用于解决成像逆问题。该库覆盖了图像重建的全部关键步骤：从高效实现正向算子（如光学、MRI、断层扫描），到变分问题的定义与求解，以及先进神经网络架构的设计与训练。本文描述了该库的主要功能，并讨论了核心设计选择。
原文摘要 · Abstract (English)
DeepInverse is an open-source PyTorch-based library for solving imaging inverse problems. The library covers all crucial steps in image reconstruction from the efficient implementation of forward operators (e.g., optics, MRI, tomography), to the definition and resolution of variational problems and the design and training of advanced neural network architectures. In this paper, we describe the main functionality of the library and discuss the main design choices.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。