End-to-end Interpretable Learning of Non-blind Image Deblurring

@inproceedings{Eboli2020EndtoendIL,
  title={End-to-end Interpretable Learning of Non-blind Image Deblurring},
  author={Thomas Eboli and Jian Sun and Jean Ponce},
  booktitle={ECCV},
  year={2020}
}
Non-blind image deblurring is typically formulated as a linear least-squares problem regularized by natural priors on the corresponding sharp picture's gradients, which can be solved, for example, using a half-quadratic splitting method with Richardson fixed-point iterations for its least-squares updates and a proximal operator for the auxiliary variable updates. We propose to precondition the Richardson solver using approximate inverse filters of the (known) blur and natural image prior… 
Nonblind Image Deconvolution via Leveraging Model Uncertainty in An Untrained Deep Neural Network
Nonblind image deconvolution (NID) is about restoring the latent image with sharp details from a noisy blurred one using a known blur kernel. This paper presents a dataset-free deep learning approach
Learning to Jointly Deblur, Demosaick and Denoise Raw Images
TLDR
An existing learningbased approach to RGB image deblurring is adapted to handle raw images by introducing a new interpretable module that jointly demosaicks and deblurs them and this model is trained on RGB images converted into raw ones following a realistic invertible camera pipeline.
Deep Model-Based Super-Resolution with Non-uniform Blur
TLDR
A fast deep plug-and-play algorithm, based on linearized ADMM splitting techniques, which can solve the super-resolution problem with spatially-varying blur and a deep unfolding architecture that handles various blur kernels, scale factors, and noise levels.
Learned Gradient of a Regularizer for Plug-and-Play Gradient Descent
TLDR
It is shown that it is possible to train a denoiser along with a network that corresponds to the gradient of its regularizer, and this gradient of the regularizer is used in gradient-based optimization methods and obtained better results comparing to other generic Plug-and-Play approaches.
Deep Camera Obscura: An Image Restoration Pipeline for Lensless Pinhole Photography
TLDR
This approach allows for more practical exposure times for hand-held photography and provides higher image quality, making it more suitable for daily photography compared to other lensless cameras while keeping size and cost low.
Learning a Non-blind Deblurring Network for Night Blurry Images
TLDR
This paper proposes a non-blind deblurring network (NBDN) to restore night blurry images, and develops a confidence estimation unit (CEU) to estimate a map which ensures smaller contributions of these pixels in the deconvolution steps which are optimized by the conjugate gradient (CG) method.
Photon Limited Non-Blind Deblurring Using Algorithm Unrolling
Image deblurring in photon-limited conditions is ubiquitous in a variety of low-light applications such as photography, microscopy and astronomy. However, the presence of photon shot noise due to
Pre-Trained Image Processing Transformer
TLDR
To maximally excavate the capability of transformer, the IPT model is presented to utilize the well-known ImageNet benchmark for generating a large amount of corrupted image pairs and the contrastive learning is introduced for well adapting to different image processing tasks.
Universal and Flexible Optical Aberration Correction Using Deep-Prior Based Deconvolution
TLDR
A PSF aware deep network is proposed, which takes the aberrant image and PSF map as input and produces the latent high quality version via incorporating deep priors, thus leading to a universal and flexible optical aberration correction method.
Using a Blur Metric to Estimate Linear Motion Blur Parameters
TLDR
The efficiency of the proposed method is demonstrated by performing some quantitative and qualitative experiments, and the relation between a blur metric, called NIDCT (Noise-Immune Discrete Cosine Transform-based), and the motion blur length is applied.

References

SHOWING 1-10 OF 54 REFERENCES
Discriminative Non-blind Deblurring
TLDR
This work proposes a discriminative model cascade for non-blind deblurring, which consists of a Gaussian CRF at each stage, based on the recently introduced regression tree fields, and trains the model by loss minimization and uses synthetically generated blur kernels to generate training data.
Douglas-Rachford Networks: Learning Both the Image Prior and Data Fidelity Terms for Blind Image Deconvolution
TLDR
A method called Dr-Net is presented, which does not require any such estimate and is further able to invert the effects of the blurring in blind image recovery tasks and is one of the fastest algorithms according to wall-clock times while doing so.
Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems
TLDR
This paper studies the possibility of replacing the proximal operator of the regularization used in many convex energy minimization algorithms by a denoising neural network, and obtains state-of-the-art reconstruction results.
Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution
TLDR
The proposed fully convolutional network is able to learn an adaptive image prior, which keeps both local and global information, and performs favorably against state-of-the-art algorithms in terms of quality and speed.
A Neural Approach to Blind Motion Deblurring
TLDR
A new method for blind motion deblurring that uses a neural network trained to compute estimates of sharp image patches from observations that are blurred by an unknown motion kernel to predict the complex Fourier coefficients of a deconvolution filter to be applied to the input patch for restoration.
Blind Deblurring Using Internal Patch Recurrence
TLDR
This paper exploits deviations from ideal patch recurrence as a cue for recovering the underlying (unknown) blur kernel k, such that if its effect is “undone” (if the blurry image is deconvolved with k), the patch similarity across scales of the image will be maximized.
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.
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.
Learning to Estimate and Remove Non-uniform Image Blur
TLDR
This paper addresses the problem of restoring images subjected to unknown and spatially varying blur caused by defocus or linear motion using a robust (non-uniform) deblurring algorithm based on sparse regularization with global image statistics.
Blind Image Deblurring Using Dark Channel Prior
TLDR
This work introduces a linear approximation of the min operator to compute the dark channel and achieves state-of-the-art results on deblurring natural images and compares favorably methods that are well-engineered for specific scenarios.
...
1
2
3
4
5
...