面向大规模三维逆问题的高效展开网络
Efficient Unrolled Networks for Large-Scale 3D Inverse Problems
把大规模前向算子通过区域分解与法算子近似嵌入展开网络，使单卡即可端到端训练含算子的 3D 重建模型；做 3D 逆问题（CT/MRI 重建）时可直接复用该显存友好的算子嵌入方案。
原文依据 we present a domain partitioning strategy and normal operator approximations that enable the training of end-to-end reconstruction models
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于深度学习的方法已经彻底改变了成像逆问题领域，在多种成像场景中取得了最优性能。性能最好的网络会将成像算子纳入网络架构之中，通常以深度展开的形式实现。然而在大规模问题（例如三维成像）中，由于全局前向算子所需内存过于庞大，多数现有方法无法在架构中纳入该算子，这也阻碍了常用的分块策略。本文提出一种区域划分策略与法算子近似方法，使得端到端重建模型的训练成为可能，并可将任意大规模问题的前向算子纳入其架构。所提方法在三维 X 射线锥束断层成像与三维多线圈加速 MRI 上取得了最优性能，且训练与推理均只需单块 GPU。
英文原文摘要 974 字符
Deep learning-based methods have revolutionized the field of imaging inverse problems, yielding state-of-the-art performance across various imaging domains. The best performing networks incorporate the imaging operator within the network architecture, typically in the form of deep unrolling. However, in large-scale problems, such as 3D imaging, most existing methods fail to incorporate the operator in the architecture due to the prohibitive amount of memory required by global forward operators, which hinders typical patching strategies. In this work, we present a domain partitioning strategy and normal operator approximations that enable the training of end-to-end reconstruction models incorporating forward operators of arbitrarily large problems into their architecture. The proposed method achieves state-of-the-art performance on 3D X-ray cone-beam tomography and 3D multi-coil accelerated MRI, while requiring only a single GPU for both training and inference.