Neural Blind Deconvolution Using Deep Priors

@article{Ren2020NeuralBD,
  title={Neural Blind Deconvolution Using Deep Priors},
  author={Dongwei Ren and K. Zhang and Qilong Wang and Qinghua Hu and Wangmeng Zuo},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
  pages={3338-3347}
}
  • Dongwei Ren, K. Zhang, +2 authors W. Zuo
  • Published 2020
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Blind deconvolution is a classical yet challenging low-level vision problem with many real-world applications. [...] Key Method In particular, we adopt an asymmetric Autoencoder with skip connections for generating latent clean image, and a fully-connected network (FCN) for generating blur kernel. Moreover, the SoftMax nonlinearity is applied to the output layer of FCN to meet the non-negative and equality constraints. The process of neural optimization can be explained as a kind of "zero-shot" self-supervised…Expand
Blind Image Deconvolution Using Deep Generative Priors
TLDR
This article proposes a novel approach to regularize the ill-posed and non-linear blind image deconvolution (blind deblurring) using deep generative networks as priors, and presents a modification of the proposed scheme that governs thedeblurring process under both generative, and classical priors. Expand
A Deep Variational Bayesian Framework for Blind Image Deblurring
TLDR
A deep variational Bayesian framework for blind image deblurring is presented that can not only achieve a promising performance with relatively simple networks, but also enhance the performance of existing DNNs fordeblurring. Expand
Deep Priors Inside an Unrolled and Adaptive Deconvolution Model
TLDR
A deblurring architecture that adopts adaptive deconvolution modules and learning based image prior solvers is proposed that can achieve a significant improvement on the convergence rate and result in an even better restoration performance. Expand
Generic Image Restoration with Flow Based Priors
TLDR
This work proposes using normalizing flows to model the distribution of the target content and to use this as a prior in a maximum a posteriori (MAP) formulation and presents experimental results for a number of different degradations on data sets varying in complexity. Expand
Unrolled Variational Bayesian Algorithm for Image Blind Deconvolution
TLDR
A variational Bayesian algorithm (VBA) for image blind deconvolution that incorporates smoothness priors on the unknown blur/image and possible affine constraints on the blur kernel is introduced. Expand
Explore Image Deblurring via Encoded Blur Kernel Space
TLDR
This paper introduces a method to encode the blur operators of an arbitrary dataset of sharp-blur image pairs into a blur kernel space that can handle unseen blur kernel, while avoiding using complicated handcrafted priors on the blur operator often found in classical methods. Expand
Flow-based Kernel Prior with Application to Blind Super-Resolution
TLDR
The proposed normalizing flow-based kernel prior (FKP) can significantly improve the kernel estimation accuracy with less parameters, runtime and memory usage, leading to stateof-the-art blind SR results. Expand
Deep Blind Video Super-resolution
TLDR
An image deconvolution method based on the image formation model of video SR to generate intermediate latent images so that some sharp image contents can be restored well and the proposed algorithm performs favorably against state-of-the-art methods. Expand
End-to-end Alternating Optimization for Blind Super Resolution
TLDR
This work designs two convolutional neural modules, namely Restorer and Estimator, which can estimate the blur kernel and restore the SR image in a single model and can largely outperform state-of-the-art methods and produce more visually favorable results at a much higher speed. Expand
Unsupervised Single Image Super-resolution Under Complex Noise
TLDR
A model-based unsupervised SisR method to deal with the general SISR task with unknown degradations, which can evidently surpass the current state of the art (SotA) method not only with a slighter model (0.34M vs 2.40M) but also faster speed. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 57 REFERENCES
Deep Image Prior
TLDR
It is shown that a randomly-initialized neural network can be used as a handcrafted prior with excellent results in standard inverse problems such as denoising, superresolution, and inpainting. Expand
Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring
TLDR
This work proposes a multi-scale convolutional neural network that restores sharp images in an end-to-end manner where blur is caused by various sources and presents a new large-scale dataset that provides pairs of realistic blurry image and the corresponding ground truth sharp image that are obtained by a high-speed camera. Expand
Normalized Blind Deconvolution
TLDR
It is shown that using the Frobenius norm to fix the scale ambiguity enables convex image priors, such as the total variation, to achieve state-of-the-art results on both synthetic and real datasets. Expand
Efficient marginal likelihood optimization in blind deconvolution
TLDR
This paper derives a simple approximated MAPk algorithm which involves only a modest modification of common MAPx, k algorithms, and shows that MAPk can, in fact, be optimized easily, with no additional computational complexity. Expand
Simultaneous Fidelity and Regularization Learning for Image Restoration
TLDR
A principled algorithm within the maximum a posterior framework to tackle image restoration with a partially known or inaccurate degradation model is proposed, which demonstrates the effectiveness of the proposed model for image deconvolution with inaccurate blur kernels, deconVolution with multiple degradations and rain streak removal. Expand
Learning Deep CNN Denoiser Prior for Image Restoration
TLDR
Experimental results demonstrate that the learned set of denoisers can not only achieve promising Gaussian denoising results but also can be used as prior to deliver good performance for various low-level vision applications. Expand
Understanding and evaluating blind deconvolution algorithms
TLDR
The previously reported failure of the naive MAP approach is explained by demonstrating that it mostly favors no-blur explanations and it is shown that since the kernel size is often smaller than the image size a MAP estimation of the kernel alone can be well constrained and accurately recover the true blur. Expand
Fast Image Deconvolution using Hyper-Laplacian Priors
TLDR
This paper describes a deconvolution approach that is several orders of magnitude faster than existing techniques that use hyper-Laplacian priors and is able to deconvolve a 1 megapixel image in less than ~3 seconds, achieving comparable quality to existing methods that take ~20 minutes. Expand
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
TLDR
This paper investigates the construction of feed-forward denoising convolutional neural networks (DnCNNs) to embrace the progress in very deep architecture, learning algorithm, and regularization method into image Denoising, and uses residual learning and batch normalization to speed up the training process as well as boost theDenoising performance. Expand
Learning a Discriminative Prior for Blind Image Deblurring
TLDR
This work forms the image prior as a binary classifier which can be achieved by a deep convolutional neural network (CNN) and is able to distinguish whether an input image is clear or not. Expand
...
1
2
3
4
5
...