# TFPnP: Tuning-free Plug-and-Play Proximal Algorithm with Applications to Inverse Imaging Problems

arXiv: https://arxiv.org/abs/2012.05703 · HTML: https://mlsanity.com/paper/2012.05703/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2020.

## Built on by (most cited first, 20 of 20)

- [Proximal Denoiser for Convergent Plug-and-Play Optimization with Nonconvex Regularization](https://mlsanity.com/paper/2201.13256/) (2022)
- [DOLCE: A Model-Based Probabilistic Diffusion Framework for Limited-Angle CT Reconstruction](https://mlsanity.com/paper/2211.12340/) (2022)
- [Infrared Small Target Detection with Scale and Location Sensitivity](https://mlsanity.com/paper/2403.19366/) (2024)
- [Frequency-Adaptive Dilated Convolution for Semantic Segmentation](https://mlsanity.com/paper/2403.05369/) (2024)
- [Atlantis: Enabling Underwater Depth Estimation with Stable Diffusion](https://mlsanity.com/paper/2312.12471/) (2023)
- [Online Deep Equilibrium Learning for Regularization by Denoising](https://mlsanity.com/paper/2205.13051/) (2022)
- [Deep Plug-and-Play Prior for Hyperspectral Image Restoration](https://mlsanity.com/paper/2209.08240/) (2022)
- [Diffusion Posterior Proximal Sampling for Image Restoration](https://mlsanity.com/paper/2402.16907/) (2024)
- [Multi-Object Tracking in the Dark](https://mlsanity.com/paper/2405.06600/) (2024)
- [CurvPnP: Plug-and-play Blind Image Restoration with Deep Curvature Denoiser](https://mlsanity.com/paper/2211.07286/) (2022)
- [Dynamic Proximal Unrolling Network for Compressive Imaging](https://mlsanity.com/paper/2107.11007/) (2021)
- [PRISTA-Net: Deep Iterative Shrinkage Thresholding Network for Coded Diffraction Patterns Phase Retrieval](https://mlsanity.com/paper/2309.04171/) (2023)
- [TRIDENT: The Nonlinear Trilogy for Implicit Neural Representations](https://mlsanity.com/paper/2311.13610/) (2023)
- [Single-Shot Plug-and-Play Methods for Inverse Problems](https://mlsanity.com/paper/2311.13682/) (2023)
- [Robust plug-and-play methods for highly accelerated non-Cartesian MRI reconstruction](https://mlsanity.com/paper/2411.01955/) (2024)
- [LoFi: Neural Local Fields for Scalable Image Reconstruction](https://mlsanity.com/paper/2411.04995/) (2024)
- [Taming Score-Based Denoisers in ADMM: A Convergent Plug-and-Play Framework](https://mlsanity.com/paper/2603.10281/) (2026)
- [Single-shot Phase Retrieval from a Fractional Fourier Transform Perspective](https://mlsanity.com/paper/2311.10950/) (2023)
- [Training-free Ultra Small Model for Universal Sparse Reconstruction in Compressed Sensing](https://mlsanity.com/paper/2501.11592/) (2025)
- [Reinforcement learning for adaptive interior point methods in convex quadratic programming](https://mlsanity.com/paper/2509.07404/) (2025)

## Abstract (arXiv)

Plug-and-Play (PnP) is a non-convex optimization framework that combines proximal algorithms, for example, the alternating direction method of multipliers (ADMM), with advanced denoising priors. Over the past few years, great empirical success has been obtained by PnP algorithms, especially for the ones that integrate deep learning-based denoisers. However, a key challenge of PnP approaches is the need for manual parameter tweaking as it is essential to obtain high-quality results across the high discrepancy in imaging conditions and varying scene content. In this work, we present a class of tuning-free PnP proximal algorithms that can determine parameters such as denoising strength, termination time, and other optimization-specific parameters automatically. A core part of our approach is a policy network for automated parameter search which can be effectively learned via a mixture of model-free and model-based deep reinforcement learning strategies. We demonstrate, through rigorous numerical and visual experiments, that the learned policy can customize parameters to different settings, and is often more efficient and effective than existing handcrafted criteria. Moreover, we discuss several practical considerations of PnP denoisers, which together with our learned policy yield state-of-the-art results. This advanced performance is prevalent on both linear and nonlinear exemplar inverse imaging problems, and in particular shows promising results on compressed sensing MRI, sparse-view CT, single-photon imaging, and phase retrieval.