DAPS++ reinterprets diffusion inverse problems as a decoupled EM-style initialization, significantly increasing restoration speed and stability.
March 19, 2026
Original Paper
DAPS++: Rethinking Diffusion Inverse Problems with Decoupled Posterior Annealing
arXiv · 2511.17038
The Takeaway
It challenges the conventional view that diffusion priors and likelihood measurements must be tightly coupled during sampling. By decoupling them, it achieves higher computational efficiency and more robust image reconstruction with fewer function evaluations than traditional score-based guidance.
From the abstract
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 diffus