In this paper, we introduce SP$^3$, a novel Plug-and-Play algorithm that accelerates maximum a posteriori image restoration by replacing denoisers with Spherical Encoders (SE) as generative priors. SP$^3$ approximates the intractable proximal prior step by utilizing the SE tightly structured latent space as a robust projection onto the natural image manifold. Alternating this projection with a closed-form data-consistency step, via Half-Quadratic Splitting, achieves stable convergence without requiring gradient computation during inference. This unique formulation unlocks "anytime" restoration capabilities, producing sharp, plausible images from the first iteration. Evaluations across a variety of image restoration tasks demonstrate that SP$^3$ achieves perceptual quality comparable to state-of-the-art zero-shot diffusion and flow methods while being $3$-$630\times$ faster.

翻译：本文提出一种新颖的即插即用算法SP$^3$，通过以球面编码器替代去噪器作为生成式先验，加速了最大后验图像复原过程。SP$^3$利用球面编码器高度紧凑的隐空间作为自然图像流形的鲁棒投影，以此近似处理棘手的近端先验步骤。通过半二次分裂技术将该投影与闭式数据一致性步骤交替执行，可在推理过程无需梯度计算的情况下实现稳定收敛。这种独特的公式化方法实现了“随时”复原能力，从首次迭代起即可生成清晰逼真的图像。在多种图像复原任务中的评估表明，SP$^3$在取得与最先进零样本扩散及流模型相当的感知质量的同时，速度提升了3至630倍。