Deblurring Using Analysis-Synthesis Networks Pair

  title={Deblurring Using Analysis-Synthesis Networks Pair},
  author={Adam Kaufman and Raanan Fattal},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  • Adam Kaufman, Raanan Fattal
  • Published 6 April 2020
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Blind image deblurring remains a challenging problem for modern artificial neural networks. Unlike other image restoration problems, deblurring networks fail behind the performance of existing deblurring algorithms in case of uniform and 3D blur models. This follows from the diverse and profound effect that the unknown blur-kernel has on the deblurring operator. We propose a new architecture which breaks the deblurring network into an analysis network which estimates the blur, and a synthesis… 

Figures and Tables from this paper

Deep Image Deblurring: A Survey
This paper presents a comprehensive and timely survey of recently published deep-learning based image deblurring approaches, aim-ing to serve the community as a useful literature review.
Non-uniform Motion Deblurring with Blurry Component Divided Guidance
LODE: Deep Local Deblurring and A New Benchmark
This paper lays the data foundation for local deblurring by constructing, for the first time, a local-deblur (LODE) dataset and proposes a novel framework, termed blur-awaredeblurring network (BladeNet), which contains three components: the Local Blur Synthesis module generates locally blurred training pairs, the LocalBlur Perception module automatically captures the locally blurred region and the Blur-guided Spatial Attention module guides the deblurred network with spatial attention.
Neural Maximum A Posteriori Estimation on Unpaired Data for Motion Deblurring
A Neural Maximum A Posteriori (NeurMAP) estimation framework for training neural networks to recover blind motion information and sharp content from unpaired data and demonstrates superiority on both quantitative metrics and visual quality over state-of-the-art methods.
Benchmarking Deep Deblurring Algorithms: A Large-Scale Multi-Cause Dataset and A New Baseline Model
A new baseline model is proposed, level-attention deblurring network, to adapt to multiple causes of blurs and derives more powerful features with larger weights assigned to more important levels, thereby enhancing the feature representation.
Pixel-Guided Dual-Branch Attention Network for Joint Image Deblurring and Super-Resolution
This work designs a novel Pixel-Guided dual-branch attention network (PDAN) that handles both image deblurring and super-resolution tasks jointly and proposes a novel loss function better focus on large and medium range errors.
Blind Non-Uniform Motion Deblurring using Atrous Spatial Pyramid Deformable Convolution and Deblurring-Reblurring Consistency
This paper proposes a new architecture which consists of multiple Atrous Spatial Pyramid Deformable Convolution (ASPDC) modules to deblur an image end-to-end with more flexibil-ity and shows that the proposed method outperforms state-of-the-art methods on the benchmark datasets.
A Deep Variational Bayesian Framework for Blind Image Deblurring


Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring
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.
Blur-Invariant Deep Learning for Blind-Deblurring
A new architecture for blind motion deblurring that consists of an autoencoder that learns the data prior, and an adversarial network that attempts to generate and discriminate between clean and blurred features is proposed.
Scale-Recurrent Network for Deep Image Deblurring
A Scale-recurrent Network (SRN-DeblurNet) is proposed and shown to produce better quality results than state-of-the-arts, both quantitatively and qualitatively in single image deblurring.
A Comparative Study for Single Image Blind Deblurring
The first comprehensive perceptual study and analysis of single image blind deblurring using real-world blurred images and the correlation between human subjective scores and several full-reference and noreference image quality metrics is studied.
DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks
DeblurGAN achieves state-of-the art performance both in the structural similarity measure and visual appearance and is 5 times faster than the closest competitor - Deep-Deblur.
High-quality motion deblurring from a single image
A new algorithm for removing motion blur from a single image is presented using a unified probabilistic model of both blur kernel estimation and unblurred image restoration and is able to produce high quality deblurred results in low computation time.
Blind Motion Deblurring Using Image Statistics
This work addresses the problem of blind motion deblurring from a single image, caused by a few moving objects, and relies on the observation that the statistics of derivative filters in images are significantly changed by blur.
Deblurring Text Images via L0-Regularized Intensity and Gradient Prior
An efficient optimization method is developed to generate reliable intermediate results for kernel estimation based on a simple yet effective L0-regularized prior based on intensity and gradient for text image deblurring.
Blind Deblurring Using Internal Patch Recurrence
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.
Deblurring shaken and partially saturated images
This work proposes a forward model that includes sensor saturation, and uses it to derive a deblurring algorithm properly treating saturated pixels, and obtains significantly better results than existing deblurred algorithms.