一个轻量级模型，能通用解决多种成像逆问题。
Reconstruct Anything Model: a lightweight general model for computational imaging
- 不迭代、不依赖特定训练，直接利用成像物理规律建模
- 在医疗影像、低光成像等任务上达到顶尖性能
- 仅需少量图像微调即可适配新任务，适合快速部署
现有基于学习的成像逆问题求解方法主要分为两类：一类是迭代算法（如插件式和扩散方法），依赖预训练去噪器，计算成本高且重建效果不佳；另一类是针对特定问题端到端训练的展开架构，但具有强问题特异性且训练昂贵。本文提出一种新型非迭代、轻量级架构，将前向算子知识（采集物理与噪声参数）融入模型，无需展开过程。该模型可统一处理去模糊、磁共振成像、计算机断层扫描、图像修复与超分辨率等多种逆问题，支持任意图像尺寸与通道类型（灰度、复数、彩色）。模型可通过少量样本（最多几张图）以自监督方式快速适配未见任务或数据集，无需真实标签。大量实验表明，其在医学成像、低光成像与显微成像中均达到先进水平。代码已开源：https://github.com/matthieutrs/ram。
原文摘要 · Abstract (English)
Most existing learning-based methods for solving imaging inverse problems can be roughly divided into two classes: iterative algorithms, such as plug-and-play and diffusion methods leveraging pretrained denoisers, and unrolled architectures that are trained end-to-end for specific imaging problems. Iterative methods in the first class are computationally costly and often yield suboptimal reconstruction performance, whereas unrolled architectures are generally problem-specific and require expensive training. In this work, we propose a novel non-iterative, lightweight architecture that incorporates knowledge about the forward operator (acquisition physics and noise parameters) without relying on unrolling. Our model is trained to solve a wide range of inverse problems, such as deblurring, magnetic resonance imaging, computed tomography, inpainting, and super-resolution, and handles arbitrary image sizes and channels, such as grayscale, complex, and color data. The proposed model can be easily adapted to unseen inverse problems or datasets with a few fine-tuning steps (up to a few images) in a self-supervised way, without ground-truth references. Throughout a series of experiments, we demonstrate state-of-the-art performance from medical imaging to low-photon imaging and microscopy. Our code is available at https://github.com/matthieutrs/ram.
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。