arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.03030eess.IVcs.CV
收藏

DDRM-PR:使用去噪扩散恢复模型的傅里叶相位检索

DDRM-PR: Fourier Phase Retrieval using Denoising Diffusion Restoration Models

DTU(丹麦技术大学);METU(中东技术大学)

Mehmet Onurcan Kaya, Figen S. Oktem

AI总结:

本文提出 DDRM-PR,将 DDRM 的无监督后验采样与交替投影结合,利用预训练无条件扩散先验从含噪 Fourier 强度等测量中求解非线性相位检索,并通过仿真与实验验证其潜力与局限。

摘要:

扩散模型已证明其作为学习先验用于求解各类逆问题的效用。然而,现有大多数方法仅限于线性逆问题。本文利用 Denoising Diffusion Restoration Models(DDRM,去噪扩散恢复模型)高效且无监督的后验采样框架,来求解非线性相位检索问题;该问题需要从仅有强度的含噪测量(如 Fourier 强度)重建图像。该方法将基于模型的交替投影方法与 DDRM 相结合,以利用预训练的无条件扩散先验进行相位检索。通过仿真和实验数据证明了其性能。结果展示了该方法改进交替投影方法的潜力,也揭示了其局限性。

英文摘要:

Diffusion models have demonstrated their utility as learned priors for solving various inverse problems. However, most existing approaches are limited to linear inverse problems. This paper exploits the efficient and unsupervised posterior sampling framework of Denoising Diffusion Restoration Models (DDRM) for the solution of nonlinear phase retrieval problem, which requires reconstructing an image from its noisy intensity-only measurements such as Fourier intensity. The approach combines the model-based alternating-projection methods with the DDRM to utilize pretrained unconditional diffusion priors for phase retrieval. The performance is demonstrated through both simulations and experimental data. Results demonstrate the potential of this approach for improving the alternating-projection methods as well as its limitations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑