SP^3：即插即用復原的球面先驗

摘要

本文介紹了 SP^3，一種新穎的即插即用演算法，透過將去噪器替換為球形編碼器作為生成先驗，來加速最大後驗影像復原。SP^3 利用 SE 結構緊密的潛在空間作為自然影像流形的穩健投影，近似不可解的近端先驗步驟。透過半二次分割，將此投影與封閉式資料一致性步驟交替進行，可在推理過程中無需計算梯度，達到穩定收斂。此獨特公式實現了「隨時」復原能力，從第一次迭代即可產生清晰、合理的影像。在各種影像復原任務的評估中，SP^3 在感知品質上可與最先進的零樣本擴散與流方法相媲美，同時速度快 3 到 630 倍。

English

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.