DAPS++: Rethinking Diffusion Inverse Problems with Decoupled Posterior Annealing
This work addresses computational inefficiency in diffusion-based inverse problem solving for image restoration, offering an incremental improvement.
The paper tackled the problem of diffusion models for inverse problems by reinterpreting them as a decoupled initialization and refinement process, resulting in DAPS++ which reduces function evaluations and steps while maintaining robust performance across image restoration tasks.
From a Bayesian perspective, score-based diffusion solves inverse problems through joint inference, embedding the likelihood with the prior to guide the sampling process. However, this formulation fails to explain its practical behavior: the prior offers limited guidance, while reconstruction is largely driven by the measurement-consistency term, leading to an inference process that is effectively decoupled from the diffusion dynamics. To clarify this structure, we reinterpret the role of diffusion in inverse problem solving as an initialization stage within an expectation--maximization (EM)--style framework, where the diffusion stage and the data-driven refinement are fully decoupled. We introduce \textbf{DAPS++}, which allows the likelihood term to guide inference more directly while maintaining numerical stability and providing insight into why unified diffusion trajectories remain effective in practice. By requiring fewer function evaluations (NFEs) and measurement-optimization steps, \textbf{DAPS++} achieves high computational efficiency and robust reconstruction performance across diverse image restoration tasks.