SP3: Spherical Priors for Plug-and-Play Restoration
Not on the map. Why?
Abstract (arXiv)
In this paper, we introduce SP3, a novel Plug-and-Play algorithm that accelerates maximum a posteriori image restoration by replacing denoisers with Spherical Encoders (SE) as generative priors. SP3 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 SP3 achieves perceptual quality comparable to state-of-the-art zero-shot diffusion and flow methods while being 3-630× faster.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 70 of its 89 references that are in the map. First posted on arXiv 15 Jun 2026.
Builds on
70 of 89 references.
References · 70
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
- 2020Denoising Diffusion Implicit Modelscited by 9,655
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
- 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
- 2022Flow Matching for Generative Modelingcited by 5,426
- 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
- 2015Fast R-CNNcited by 2,930
- 2016Density estimation using Real NVPcited by 2,029
- 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
- 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
- 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
38 more
- 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
- 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
- 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
- 2018Demystifying MMD GANscited by 1,268
- 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
- 2016Colorful Image Colorizationcited by 1,113
- 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
- 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
- 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 960
- 2022Denoising Diffusion Restoration Modelscited by 951
- 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 897
- 2017The Perception-Distortion Tradeoffcited by 582
- 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Modelcited by 574
- 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 467
- 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 407
- 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358
- 2017Compressed Sensing using Generative Modelscited by 337
- 2023Denoising Diffusion Models for Plug-and-Play Image Restorationcited by 335
- 2016The Little Engine that Could: Regularization by Denoising (RED)cited by 303
- 2023DiffBIR: Towards Blind Image Restoration with Generative Diffusion Priorcited by 255
- 2021Deblurring via Stochastic Refinementcited by 248
- 2022Towards Robust Blind Face Restoration with Codebook Lookup Transformercited by 230
- 2020Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulationcited by 225
- 2023A Variational Perspective on Solving Inverse Problems with Diffusion Modelscited by 217
- 2020SRFlow: Learning the Super-Resolution Space with Normalizing Flowcited by 209
- 2019Diagnosing and Enhancing VAE Modelscited by 192
- 2023Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restorationcited by 164
- 2023Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Modelscited by 156
- 2015Learning a Convolutional Neural Network for Non-uniform Motion Blur Removalcited by 148
- 2022VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decodercited by 116
- 2024D-Flow: Differentiating through Flows for Controlled Generationcited by 115
- 2021Gradient Step Denoiser for convergent Plug-and-Playcited by 107
- 2022DifFace: Blind Face Restoration with Diffused Error Contractioncited by 96
- 2019Invertible generative models for inverse problems: mitigating representation error and dataset biascited by 93
- 2024PnP-Flow: Plug-and-Play Image Restoration with Flow Matchingcited by 92
- 2018Taming VAEscited by 85
- 2025EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modelingcited by 85
- 2018Phase Retrieval Under a Generative Priorcited by 73
50 most cited of 70 All 70 (JSON)
Built on by
Citing papers per year: 2026: 1.
1 paper.
- 2026Sphere Encoder 2cited by 0
- 2026Sphere Encoder 21 Oct 2026