Integrating Intermediate Layer Optimization and Projected Gradient Descent for Solving Inverse Problems with Diffusion Models

Inverse problems (IPs) involve reconstructing signals from noisy observations. Traditional approaches often rely on handcrafted priors, which can fail to capture the complexity of real-world data. The advent of pre-trained generative models has introduced new paradigms, offering improved reconstructions by learning rich priors from data. Among these, diffusion models (DMs) have emerged as a powerful framework, achieving remarkable reconstruction performance across numerous IPs. However, existing DM-based methods frequently encounter issues such as heavy computational demands and suboptimal convergence. In this work, building upon the idea of the recent work DMPlug~\cite{wang2024dmplug}, we propose two novel methods, DMILO and DMILO-PGD, to address these challenges. Our first method, DMILO, employs intermediate layer optimization (ILO) to alleviate the memory burden inherent in DMPlug. Additionally, by introducing sparse deviations, we expand the range of DMs, enabling the exploration of underlying signals that may lie outside the range of the diffusion model. We further propose DMILO-PGD, which integrates ILO with projected gradient descent (PGD), thereby reducing the risk of suboptimal convergence. We provide an intuitive theoretical analysis of our approach under appropriate conditions and validate its superiority through extensive experiments on diverse image datasets, encompassing both linear and nonlinear IPs. Our results demonstrate significant performance gains over state-of-the-art methods, highlighting the effectiveness of DMILO and DMILO-PGD in addressing common challenges in DM-based IP solvers.