Denoising Diffusion Models for Plug-and-Play Image Restoration

Plug-and-play Image Restoration (IR) has been widely recognized as a flexible and interpretable method for solving various inverse problems by utilizing any off-the-shelf denoiser as the implicit image prior. However, most existing methods focus on discriminative Gaussian denoisers. Although diffusion models have shown impressive performance for high-quality image synthesis, their potential to serve as a generative denoiser prior to the plug-and-play IR methods remains to be further explored. While several other attempts have been made to adopt diffusion models for image restoration, they either fail to achieve satisfactory results or typically require an unacceptable number of Neural Function Evaluations (NFEs) during inference. This paper proposes DiffPIR, which integrates the traditional plug-and-play method into the diffusion sampling framework. Compared to plug-and-play IR methods that rely on discriminative Gaussian denoisers, DiffPIR is expected to inherit the generative ability of diffusion models. Experimental results on three representative IR tasks, including super-resolution, image deblurring, and inpainting, demonstrate that DiffPIR achieves state-of-the-art performance on both the FFHQ and ImageNet datasets in terms of reconstruction faithfulness and perceptual quality with no more than 100 NFEs. The source code is available at {\url{https://github.com/yuanzhi-zhu/DiffPIR}}

[1]  David J. Fleet,et al.  Image Super-Resolution via Iterative Refinement , 2021, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Michael T. McCann,et al.  Diffusion Posterior Sampling for General Noisy Inverse Problems , 2022, ICLR.

[3]  Jonathan Ho Classifier-Free Diffusion Guidance , 2022, ArXiv.

[4]  Tero Karras,et al.  Elucidating the Design Space of Diffusion-Based Generative Models , 2022, NeurIPS.

[5]  Jakub M. Tomczak,et al.  On Analyzing Generative and Denoising Capabilities of Diffusion-based Deep Generative Models , 2022, NeurIPS.

[6]  Saeed Ranjbar Alvar,et al.  Joint image compression and denoising via latent-space scalability , 2022, Frontiers in Signal Processing.

[7]  Prafulla Dhariwal,et al.  Hierarchical Text-Conditional Image Generation with CLIP Latents , 2022, ArXiv.

[8]  Michael Elad,et al.  Denoising Diffusion Restoration Models , 2022, NeurIPS.

[9]  L. Gool,et al.  RePaint: Inpainting using Denoising Diffusion Probabilistic Models , 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Prafulla Dhariwal,et al.  GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models , 2021, ICML.

[11]  Karsten Kreis,et al.  Tackling the Generative Learning Trilemma with Denoising Diffusion GANs , 2021, ICLR.

[12]  Jong-Chul Ye,et al.  Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction , 2021, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Ming-Hsuan Yang,et al.  Learning Discriminative Shrinkage Deep Networks for Image Deconvolution , 2021, ECCV.

[14]  David J. Fleet,et al.  Palette: Image-to-Image Diffusion Models , 2021, SIGGRAPH.

[15]  Karen Egiazarian,et al.  Learning-Based Noise Component Map Estimation for Image Denoising , 2021, IEEE Signal Processing Letters.

[16]  Yonina C. Eldar,et al.  Deep Unfolding With Normalizing Flow Priors for Inverse Problems , 2021, IEEE Transactions on Signal Processing.

[17]  Valentin De Bortoli,et al.  Bayesian imaging using Plug & Play priors: when Langevin meets Tweedie , 2021, SIAM J. Imaging Sci..

[18]  Luc Van Gool,et al.  Plug-and-Play Image Restoration With Deep Denoiser Prior , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Mikael Le Pendu,et al.  Learned Gradient of a Regularizer for Plug-and-Play Gradient Descent , 2022, ArXiv.

[20]  Youngjune Gwon,et al.  ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[21]  Prafulla Dhariwal,et al.  Diffusion Models Beat GANs on Image Synthesis , 2021, NeurIPS.

[22]  Prafulla Dhariwal,et al.  Improved Denoising Diffusion Probabilistic Models , 2021, ICML.

[23]  Abhishek Kumar,et al.  Score-Based Generative Modeling through Stochastic Differential Equations , 2020, ICLR.

[24]  Jiaming Song,et al.  Denoising Diffusion Implicit Models , 2020, ICLR.

[25]  Eero P. Simoncelli,et al.  Stochastic Solutions for Linear Inverse Problems using the Prior Implicit in a Denoiser , 2021, NeurIPS.

[26]  Pieter Abbeel,et al.  Denoising Diffusion Probabilistic Models , 2020, NeurIPS.

[27]  Dmitry Vetrov,et al.  A Prior of a Googol Gaussians: a Tensor Ring Induced Prior for Generative Models , 2019, NeurIPS.

[28]  Cheng Chen,et al.  PnP-AdaNet: Plug-and-Play Adversarial Domain Adaptation Network at Unpaired Cross-Modality Cardiac Segmentation , 2019, IEEE Access.

[29]  Yang Song,et al.  Generative Modeling by Estimating Gradients of the Data Distribution , 2019, NeurIPS.

[30]  Ali Razavi,et al.  Generating Diverse High-Fidelity Images with VQ-VAE-2 , 2019, NeurIPS.

[31]  Xiaohan Chen,et al.  Plug-and-Play Methods Provably Converge with Properly Trained Denoisers , 2019, ICML.

[32]  Lei Zhang,et al.  Deep Plug-And-Play Super-Resolution for Arbitrary Blur Kernels , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  Timo Aila,et al.  A Style-Based Generator Architecture for Generative Adversarial Networks , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[34]  Eric Moulines,et al.  Efficient Bayesian Computation by Proximal Markov Chain Monte Carlo: When Langevin Meets Moreau , 2016, SIAM J. Imaging Sci..

[35]  Hassan Mansour,et al.  A Plug-and-Play Priors Approach for Solving Nonlinear Imaging Inverse Problems , 2017, IEEE Signal Processing Letters.

[36]  Hiroshi Ishikawa,et al.  Globally and locally consistent image completion , 2017, ACM Trans. Graph..

[37]  Michael Möller,et al.  Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[38]  Wangmeng Zuo,et al.  Learning Deep CNN Denoiser Prior for Image Restoration , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[39]  Michael Elad,et al.  The Little Engine That Could: Regularization by Denoising (RED) , 2016, SIAM J. Imaging Sci..

[40]  Samy Bengio,et al.  Density estimation using Real NVP , 2016, ICLR.

[41]  Stanley H. Chan,et al.  Plug-and-Play ADMM for Image Restoration: Fixed-Point Convergence and Applications , 2016, IEEE Transactions on Computational Imaging.

[42]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[43]  Surya Ganguli,et al.  Deep Unsupervised Learning using Nonequilibrium Thermodynamics , 2015, ICML.

[44]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[45]  Xiaoou Tang,et al.  Learning a Deep Convolutional Network for Image Super-Resolution , 2014, ECCV.

[46]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[47]  Stephen P. Boyd,et al.  Proximal Algorithms , 2013, Found. Trends Optim..

[48]  Brendt Wohlberg,et al.  Plug-and-Play priors for model based reconstruction , 2013, 2013 IEEE Global Conference on Signal and Information Processing.

[49]  Karen O. Egiazarian,et al.  BM3D Frames and Variational Image Deblurring , 2011, IEEE Transactions on Image Processing.

[50]  B. Efron Tweedie’s Formula and Selection Bias , 2011, Journal of the American Statistical Association.

[51]  Stephen P. Boyd,et al.  Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers , 2011, Found. Trends Mach. Learn..

[52]  Alessandro Foi,et al.  Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering , 2007, IEEE Transactions on Image Processing.

[53]  Aapo Hyvärinen,et al.  Estimation of Non-Normalized Statistical Models by Score Matching , 2005, J. Mach. Learn. Res..

[54]  Jean-Michel Morel,et al.  A non-local algorithm for image denoising , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[55]  Donald Geman,et al.  Nonlinear image recovery with half-quadratic regularization , 1995, IEEE Trans. Image Process..

[56]  B. Anderson Reverse-time diffusion equation models , 1982 .