用随机恢复模型提升图像逆问题重建效果，无需重新训练即可超越现有方法。
Stochastic Deep Restoration Priors for Imaging Inverse Problems
- 利用多个通用修复模型的集成作为正则化先验
- 在磁共振成像和超分辨率任务中达到顶尖性能
- 可自监督训练，适合数据不全的场景
深度神经网络作为图像去噪器广泛用于图像逆问题求解。尽管高斯去噪被认为足以学习图像先验，我们发现以更通用的恢复操作预训练的深度模型所生成的先验表现更优。本文提出随机深度恢复先验（ShaRP），通过集成此类恢复模型来正则化逆问题。相比使用高斯去噪器先验的方法，ShaRP能更好处理结构化伪影，并在无全采样数据时实现自监督训练。我们证明了ShaRP最小化一个包含基于最小均方误差（MMSE）恢复算子得分函数的正则项的目标函数，并理论分析其收敛性。实验表明，该方法在磁共振成像重建和单图超分辨率等任务上表现优异，优于基于去噪器与扩散模型的方法，且无需重新训练。
原文摘要 · Abstract (English)
Deep neural networks trained as image denoisers are widely used as priors for solving imaging inverse problems. While Gaussian denoising is thought sufficient for learning image priors, we show that priors from deep models pre-trained as more general restoration operators can perform better. We introduce Stochastic deep Restoration Priors (ShaRP), a novel method that leverages an ensemble of such restoration models to regularize inverse problems. ShaRP improves upon methods using Gaussian denoiser priors by better handling structured artifacts and enabling self-supervised training even without fully sampled data. We prove ShaRP minimizes an objective function involving a regularizer derived from the score functions of minimum mean square error (MMSE) restoration operators, and theoretically analyze its convergence. Empirically, ShaRP achieves state-of-the-art performance on tasks such as magnetic resonance imaging reconstruction and single-image super-resolution, surpassing both denoiser-and diffusion-model-based methods without requiring retraining.
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。