SP^3：适用于即插即用的球形修复方法
SP^3: Spherical Priors for Plug-and-Play Restoration
摘要
在本文中，我们介绍了SP^3这一创新的“即插即用”算法。该算法通过将去噪器替换为球形编码器作为生成先验，从而加速最大后验图像恢复过程。SP^3通过利用球形编码器的结构化潜在空间来近似难以处理的近似先验，从而实现稳健的投影操作，使得图像能够在自然图像流形上稳定收敛。通过半二次分割技术，这种投影操作与封闭形式的数据一致性步骤相结合，使得算法在无需计算梯度的情况下也能实现稳定收敛。这种独特的算法结构使得算法能够“随时”进行图像恢复，从第一次迭代就能得到清晰、可信的图像。在多种图像恢复任务的评估中可以看出，SP^3在感知质量方面达到了与当前最先进的零样本扩散和流动方法相当的水平，同时其运行速度则快了3到630倍。
English Abstract
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 3-630times faster.