论文标题
Dolph：相检索的扩散模型
DOLPH: Diffusion Models for Phase Retrieval
论文作者
论文摘要
相检索是指从其复杂值线性测量的大小中恢复图像的问题。由于问题不足，因此恢复需要对未知图像的先验知识。我们将Dolph作为一个新的基于深层模型的体系结构，用于相位检索，该体系结构集成了使用扩散模型的图像，该图像具有扩散模型，该模型与非convex data-Fidelity项用于相位检索。扩散模型是最近的一类深层生成模型，由于其作为图像Denoisers的实现，它们相对容易训练。 Dolph通过将数据矛盾更新与扩散模型的采样步骤交替来重建高质量的解决方案。我们的数值结果表明，鉴于一组测量值，Dolph对噪声的鲁棒性及其产生多种候选解决方案的能力。
Phase retrieval refers to the problem of recovering an image from the magnitudes of its complex-valued linear measurements. Since the problem is ill-posed, the recovery requires prior knowledge on the unknown image. We present DOLPH as a new deep model-based architecture for phase retrieval that integrates an image prior specified using a diffusion model with a nonconvex data-fidelity term for phase retrieval. Diffusion models are a recent class of deep generative models that are relatively easy to train due to their implementation as image denoisers. DOLPH reconstructs high-quality solutions by alternating data-consistency updates with the sampling step of a diffusion model. Our numerical results show the robustness of DOLPH to noise and its ability to generate several candidate solutions given a set of measurements.
