REPNP: Plug-and-Play with Deep Reinforcement Learning Prior for Robust Image Restoration

07/25/2022
by   Chong Wang, et al.
0

Image restoration schemes based on the pre-trained deep models have received great attention due to their unique flexibility for solving various inverse problems. In particular, the Plug-and-Play (PnP) framework is a popular and powerful tool that can integrate an off-the-shelf deep denoiser for different image restoration tasks with known observation models. However, obtaining the observation model that exactly matches the actual one can be challenging in practice. Thus, the PnP schemes with conventional deep denoisers may fail to generate satisfying results in some real-world image restoration tasks. We argue that the robustness of the PnP framework is largely limited by using the off-the-shelf deep denoisers that are trained by deterministic optimization. To this end, we propose a novel deep reinforcement learning (DRL) based PnP framework, dubbed RePNP, by leveraging a light-weight DRL-based denoiser for robust image restoration tasks. Experimental results demonstrate that the proposed RePNP is robust to the observation model used in the PnP scheme deviating from the actual one. Thus, RePNP can generate more reliable restoration results for image deblurring and super resolution tasks. Compared with several state-of-the-art deep image restoration baselines, RePNP achieves better results subjective to model deviation with fewer model parameters.

READ FULL TEXT
research
08/31/2020

Plug-and-Play Image Restoration with Deep Denoiser Prior

Recent works on plug-and-play image restoration have shown that a denois...
research
05/15/2023

Denoising Diffusion Models for Plug-and-Play Image Restoration

Plug-and-play Image Restoration (IR) has been widely recognized as a fle...
research
09/17/2022

Deep Plug-and-Play Prior for Hyperspectral Image Restoration

Deep-learning-based hyperspectral image (HSI) restoration methods have g...
research
06/13/2022

One Size Fits All: Hypernetwork for Tunable Image Restoration

We introduce a novel approach for tunable image restoration that achieve...
research
07/12/2021

R3L: Connecting Deep Reinforcement Learning to Recurrent Neural Networks for Image Denoising via Residual Recovery

State-of-the-art image denoisers exploit various types of deep neural ne...
research
04/19/2019

Deep Likelihood Network for Image Restoration with Multiple Degradations

Convolutional neural networks have been proven very effective in a varie...
research
09/12/2023

A 3M-Hybrid Model for the Restoration of Unique Giant Murals: A Case Study on the Murals of Yongle Palace

The Yongle Palace murals, as valuable cultural heritage, have suffered v...

Please sign up or login with your details

Forgot password? Click here to reset