Abstract
Recently, Deep Unfolding Networks (DUNs) have achieved impressive reconstruction quality in the field of image Compressive Sensing (CS) by unfolding iterative optimization algorithms into neural networks. The reconstruction quality of DUNs depends on the learned prior knowledge, so introducing stronger prior knowledge can further improve reconstruction quality. On the other hand, pre-trained diffusion models contain powerful prior knowledge and have a solid theoretical foundation and strong scalability, but it requires a large number of iterative steps to achieve reconstruction. In this paper, we propose to use the powerful prior knowledge of pre-trained diffusion model in DUNs to achieve high-quality reconstruction with less steps for image CS. Specifically, we first design an iterative optimization algorithm named Diffusion Message Passing (DMP), which embeds a pre-trained diffusion model into each iteration process of DMP. Then, we deeply unfold the DMP algorithm into a neural network named DMP-DUN. The proposed DMP-DUN can use lightweight neural networks to achieve mapping from measurement data to the intermediate steps of the reverse diffusion process and directly approximate the divergence of the diffusion model, thereby further improving reconstruction efficiency. Extensive experiments show that our proposed DMP-DUN achieves state-of-the-art performance and requires at least only 2 steps to reconstruct the image. Codes are available at this https URL.
Abstract (translated)
最近，深度展开网络（DUNs）通过将迭代优化算法展开放到神经网络中，在图像压缩感知（CS）领域实现了令人印象深刻的重建质量。DUNs的重建质量依赖于所学习的先验知识，因此引入更强的先验知识可以进一步提高重建质量。另一方面，预训练扩散模型含有强大的先验知识，并具有坚实的理论基础和很强的扩展性，但需要大量的迭代步骤才能实现重建。在本文中，我们提出将预训练扩散模型的强大先验知识用于DUNs，以通过较少的步骤实现高质量的图像CS重建。 具体来说，我们首先设计了一个名为扩散信息传递（DMP）的迭代优化算法，在每次DMP迭代过程中嵌入一个预训练的扩散模型。然后，我们将DMP算法深度展开成一个称为DMP-DUN的神经网络。所提出的DMP-DUN可以使用轻量级的神经网络来实现从测量数据到逆向扩散过程中间步骤的映射，并直接逼近扩散模型的散度，从而进一步提高重建效率。 广泛的实验表明，我们提出的方法DMP-DUN达到了最先进的性能，并且只需要最少2步就能重建图像。代码可在该链接获取：[请在此处插入实际URL]。
URL
https://arxiv.org/abs/2503.08429
