DGSolver：面向图像复原的通用后验采样扩散通才求解器
DGSolver: Diffusion Generalist Solver with Universal Posterior Sampling for Image Restoration
AI总结：
本文提出DGSolver，通过推导通才扩散模型的精确常微分方程、设计高阶求解器与队列加速采样策略，并集成通用后验采样修正逆向推理误差，在图像复原精度、稳定性和可扩展性上超越现有方法。
摘要：
扩散模型在通用图像复原中已取得显著进展。现有方法通过减少采样步数来加速推理，但较大的步长间隔往往会引入累积误差。此外，它们难以在退化表示的通用性与复原质量之间取得平衡。为解决这些挑战，我们提出DGSolver，一种具有通用后验采样的扩散通才求解器。我们首先推导出通才扩散模型的精确常微分方程，并针对性地设计高阶求解器，配合基于队列的加速采样策略，以同时提升精度和效率。随后，我们集成通用后验采样以更好地逼近流形约束梯度，从而获得更准确的噪声估计并修正逆向推理中的误差。大量实验表明，DGSolver在复原精度、稳定性和可扩展性方面，无论定性还是定量，均优于当前最先进的方法。代码和模型将在https://github.com/MiliLab/DGSolver发布。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
