提出新方法让大尺度3D成像逆问题用单卡训练，性能领先。
Efficient Unrolled Networks for Large-Scale 3D Inverse Problems
- 通过域分割与算子近似，实现大模型嵌入正向算子
- 3D X射线与多线圈MRI重建精度达当前最优
- 仅需单张显卡完成训练与推理，适合资源受限场景
基于深度学习的方法已显著推动成像逆问题的发展，在多个成像领域取得顶尖性能。最先进网络通常将成像算子嵌入架构中，常见形式为深层展开（deep unrolling）。然而在大规模问题如3D成像中，现有方法因全局前向算子所需内存过高，难以融入架构，传统分块策略亦受限。本文提出域分割策略与正规算子近似方法，使端到端重建模型可嵌入任意规模的前向算子。该方法在3D X射线锥束断层成像和3D多线圈加速MRI任务上达到当前最优性能，且训练与推理仅需单张GPU。
原文摘要 · Abstract (English)
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 hinder 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.
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。