CVApr 30, 2025

DGSolver: Diffusion Generalist Solver with Universal Posterior Sampling for Image Restoration

arXiv:2504.21487v25 citationsh-index: 8Has Code
Originality Incremental advance
AI Analysis

This addresses image restoration challenges for computer vision applications, representing an incremental improvement with novel method elements.

The paper tackles the problem of cumulative errors and degradation representation balance in diffusion models for image restoration by introducing DGSolver, which uses exact ODEs, high-order solvers, and universal posterior sampling to improve accuracy and efficiency. Results show it outperforms state-of-the-art methods in restoration accuracy, stability, and scalability.

Diffusion models have achieved remarkable progress in universal image restoration. While existing methods speed up inference by reducing sampling steps, substantial step intervals often introduce cumulative errors. Moreover, they struggle to balance the commonality of degradation representations and restoration quality. To address these challenges, we introduce \textbf{DGSolver}, a diffusion generalist solver with universal posterior sampling. We first derive the exact ordinary differential equations for generalist diffusion models and tailor high-order solvers with a queue-based accelerated sampling strategy to improve both accuracy and efficiency. We then integrate universal posterior sampling to better approximate manifold-constrained gradients, yielding a more accurate noise estimation and correcting errors in inverse inference. Extensive experiments show that DGSolver outperforms state-of-the-art methods in restoration accuracy, stability, and scalability, both qualitatively and quantitatively. Code and models will be available at https://github.com/MiliLab/DGSolver.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes