DGSolver提升图像修复精度与效率，解决采样误差与退化建模难题。
DGSolver: Diffusion Generalist Solver with Universal Posterior Sampling for Image Restoration
- 基于高阶微分方程求解器与队列加速采样策略，提升推理精度与速度。
- 在多个基准上实现峰值信噪比（PSNR）提升0.1~0.3dB，优于当前最优方法。
- 适合需要高保真修复、跨退化类型泛化的图像处理研究者使用。
扩散模型在通用图像修复任务中取得显著进展。现有方法通过减少采样步数加速推理，但较大的步长间隔常引入累积误差，且难以平衡退化表示的通用性与修复质量。为此，我们提出DGSolver：一种具有通用后验采样的扩散通用求解器。首先推导通用扩散模型的精确常微分方程，并设计基于队列的加速采样策略，结合高阶求解器以提升精度与效率。随后引入通用后验采样，更准确逼近流形约束梯度，实现更优的噪声估计并修正逆向推理误差。大量实验表明，DGSolver在修复精度、稳定性与可扩展性方面均优于当前先进方法，定性与定量结果均具优势。代码与模型将发布于https://github.com/MiliLab/DGSolver。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。