Learning Deep CNN Denoiser Priors for Depth Image Inpainting

Li, Zun; Wu, Jin

doi:10.3390/app9061103

Cited by 19 publications

(10 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In[40], Tirer and Giryes proposed use the IRCNN denoisers for plug-and-play SISR. In[41], Li and Wu plugged the IRCNN denoisers into the split Bregman iteration algorithm to solve depth image inpainting. In[42], Ryu et al provided the theoretical convergence analysis of plug-and-play IR based on forward-backward splitting algorithm and ADMM algorithm, and proposed spectral normalization to train a DnCNN denoiser.…”

mentioning

confidence: 99%

Plug-and-Play Image Restoration With Deep Denoiser Prior

Zhang¹,

Li²,

Zuo

et al. 2022

IEEE Trans. Pattern Anal. Mach. Intell.

489

331

View full text Add to dashboard Cite

Recent works on plug-and-play image restoration have shown that a denoiser can implicitly serve as the image prior for model-based methods to solve many inverse problems. Such a property induces considerable advantages for plug-and-play image restoration (e.g., integrating the flexibility of model-based method and effectiveness of learning-based methods) when the denoiser is discriminatively learned via deep convolutional neural network (CNN) with large modeling capacity. However, while deeper and larger CNN models are rapidly gaining popularity, existing plug-and-play image restoration hinders its performance due to the lack of suitable denoiser prior. In order to push the limits of plug-and-play image restoration, we set up a benchmark deep denoiser prior by training a highly flexible and effective CNN denoiser. We then plug the deep denoiser prior as a modular part into a half quadratic splitting based iterative algorithm to solve various image restoration problems. We, meanwhile, provide a thorough analysis of parameter setting, intermediate results and empirical convergence to better understand the working mechanism. Experimental results on three representative image restoration tasks, including deblurring, super-resolution and demosaicing, demonstrate that the proposed plug-and-play image restoration with deep denoiser prior not only significantly outperforms other state-of-the-art model-based methods but also achieves competitive or even superior performance against state-of-the-art learning-based methods. The source code is available at https://github.com/cszn/DPIR.

show abstract

mentioning

confidence: 99%

Plug-and-Play Image Restoration With Deep Denoiser Prior

Zhang¹,

Li²,

Zuo

et al. 2022

IEEE Trans. Pattern Anal. Mach. Intell.

489

331

View full text Add to dashboard Cite

show abstract

“…Tirer and Giryes [37] utilized the plug-and-play framework with IRCNN [38] denoiser to tackle single image super-resolution (SISR). Li and Wu [39] introduced IRCNN denoiser into a modelbased method to solve depth image inpainting. Zhang et al [13] modulated the deep denoiser prior into traditional modelbased methods to solve various image restoration problems.…”

Section: Model-based Methods With Deep Image Priorsmentioning

confidence: 99%

Incorporating Deep Background Prior Into Model-Based Method for Unsupervised Moving Vehicle Detection in Satellite Videos

Xiao

Liu

Ying

et al. 2023

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

“…CNN with total variation (TV) reduced the effect of noise pixels [189]. Spliting Bregman iteration algorithm and CNN [113] can enhance pixels through image depth to obtain the latent clean image. A dual-stage CNN with feature matching can better recover the detailed information of the clean image, especially noisy images [172].…”

Section: The Combination Of Optimization Methods and Cnn/nn For Awni ...mentioning

confidence: 99%

Deep Learning on Image Denoising: An overview

Tian

Zhang

Zheng³

et al. 2019

Preprint

View full text Add to dashboard Cite

Deep learning techniques have obtained much attention in image denoising. However, deep learning methods of different types deal with the noise have enormous differences. Specifically, discriminative learning based on deep learning can well address the Gaussian noise. Optimization model methods based on deep learning have good effect on estimating of the real noise. So far, there are little related researches to summarize different deep learning techniques for image denoising. In this paper, we make such a comparative study of different deep techniques in image denoising. We first classify the (1) deep convolutional neural networks (CNNs) for additive white noisy images, (2) deep CNNs for real noisy images, (3) deep CNNs for blind denoising and (4) deep CNNs for hybrid noisy images, which is the combination of noisy, blurred and low-resolution images. Then, we analyze the motivations and principles of deep learning methods of different types. Next, we compare and verify the state-of-the-art methods on public denoising datasets in terms of quantitative and qualitative analysis. Finally, we point out some potential challenges and directions of future research.

show abstract

Learning Deep CNN Denoiser Priors for Depth Image Inpainting

Cited by 19 publications

References 28 publications

Plug-and-Play Image Restoration With Deep Denoiser Prior

Plug-and-Play Image Restoration With Deep Denoiser Prior

Incorporating Deep Background Prior Into Model-Based Method for Unsupervised Moving Vehicle Detection in Satellite Videos

Deep Learning on Image Denoising: An overview

Contact Info

Product

Resources

About