# Deep Mean-Shift Priors for Image Restoration

arXiv: https://arxiv.org/abs/1709.03749 · HTML: https://mlsanity.com/paper/1709.03749/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Sep 2017.

## Built on by (most cited first, 30 of 34)

- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [Learning to Optimize: A Primer and A Benchmark](https://mlsanity.com/paper/2103.12828/) (2021)
- [SNIPS: Solving Noisy Inverse Problems Stochastically](https://mlsanity.com/paper/2105.14951/) (2021)
- [Gradient Step Denoiser for convergent Plug-and-Play](https://mlsanity.com/paper/2110.03220/) (2021)
- [Bayesian imaging using Plug & Play priors: when Langevin meets Tweedie](https://mlsanity.com/paper/2103.04715/) (2021)
- [Deep Image Deblurring: A Survey](https://mlsanity.com/paper/2201.10700/) (2022)
- [Monte Carlo guided Diffusion for Bayesian linear inverse problems](https://mlsanity.com/paper/2308.07983/) (2023)
- [Provable Probabilistic Imaging using Score-Based Generative Priors](https://mlsanity.com/paper/2310.10835/) (2023)
- [DWDN: Deep Wiener Deconvolution Network for Non-Blind Image Deblurring](https://mlsanity.com/paper/2103.09962/) (2021)
- [Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel](https://mlsanity.com/paper/2107.00986/) (2021)
- [Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior](https://mlsanity.com/paper/2103.01648/) (2021)
- [ADIR: Adaptive Diffusion for Image Reconstruction](https://mlsanity.com/paper/2212.03221/) (2022)
- [Fixed-Point and Objective Convergence of Plug-and-Play Algorithms](https://mlsanity.com/paper/2104.10348/) (2021)
- [Learning local regularization for variational image restoration](https://mlsanity.com/paper/2102.06155/) (2021)
- [HQ-50K: A Large-scale, High-quality Dataset for Image Restoration](https://mlsanity.com/paper/2306.05390/) (2023)
- [Provably Convergent Plug-and-Play Quasi-Newton Methods](https://mlsanity.com/paper/2303.07271/) (2023)
- [Bayesian Image Super-Resolution with Deep Modeling of Image Statistics](https://mlsanity.com/paper/2204.00623/) (2022)
- [Prior Mismatch and Adaptation in PnP-ADMM with a Nonconvex Convergence Analysis](https://mlsanity.com/paper/2310.00133/) (2023)
- [MeanShift++: Extremely Fast Mode-Seeking With Applications to Segmentation and Object Tracking](https://mlsanity.com/paper/2104.00303/) (2021)
- [A Dive into SAM Prior in Image Restoration](https://mlsanity.com/paper/2305.13620/) (2023)
- [Deep learning in motion deblurring: current status, benchmarks and future prospects](https://mlsanity.com/paper/2401.05055/) (2024)
- [CrossZoom: Simultaneously Motion Deblurring and Event Super-Resolving](https://mlsanity.com/paper/2309.16949/) (2023)
- [GridShift: A Faster Mode-seeking Algorithm for Image Segmentation and Object Tracking](https://mlsanity.com/paper/2206.02200/) (2022)
- [Bayesian ECG reconstruction using denoising diffusion generative models](https://mlsanity.com/paper/2401.05388/) (2023)
- [Real-World Adverse Weather Image Restoration via Dual-Level Reinforcement Learning with High-Quality Cold Start](https://mlsanity.com/paper/2511.05095/) (2025)
- [Learning Discriminative Shrinkage Deep Networks for Image Deconvolution](https://mlsanity.com/paper/2111.13876/) (2021)
- [Robustness and Exploration of Variational and Machine Learning Approaches to Inverse Problems: An Overview](https://mlsanity.com/paper/2402.12072/) (2024)
- [MAP-based Problem-Agnostic diffusion model for Inverse Problems](https://mlsanity.com/paper/2501.15128/) (2025)
- [Moir'eXNet: Adaptive Multi-Scale Demoir'eing with Linear Attention Test-Time Training and Truncated Flow Matching Prior](https://mlsanity.com/paper/2506.15929/) (2025)
- [The Third Challenge on Image Denoising at NTIRE 2026: Methods and Results](https://mlsanity.com/paper/2606.16031/) (2026)

## Abstract (arXiv)

In this paper we introduce a natural image prior that directly represents a Gaussian-smoothed version of the natural image distribution. We include our prior in a formulation of image restoration as a Bayes estimator that also allows us to solve noise-blind image restoration problems. We show that the gradient of our prior corresponds to the mean-shift vector on the natural image distribution. In addition, we learn the mean-shift vector field using denoising autoencoders, and use it in a gradient descent approach to perform Bayes risk minimization. We demonstrate competitive results for noise-blind deblurring, super-resolution, and demosaicing.