Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

computer-vision-9

Blind Image Deblurring

3260 papers • 126 benchmarks • 313 datasets

Blind Image Deblurring is a classical problem in image processing and computer vision, which aims to recover a latent image from a blurred input. Source: Learning a Discriminative Prior for Blind Image Deblurring

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in blind-image-deblurring-9

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

Use these libraries to find blind-image-deblurring-9 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Spatially-Adaptive Filter Units for Compact and Efficient Deep Neural Networks

Domen Tabernik, A. Leonardis, M. Kristan•Tue Feb 19 2019

DAUs provide a seamless substitution of convolutional filters in existing state-of-the-art architectures, which are demonstrated on AlexNet, ResNet50, ResNet101, DeepLab and SRN-DeblurNet and SRN-DeblurNet.

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

Learning Deep Gradient Descent Optimization for Image Deconvolution

Chunhua Shen, Javen Qinfeng Shi, Yanning Zhang, Dong Gong, Zhen Zhang, A. van den Hengel•Mon Apr 09 2018

A recurrent gradient descent network (RGDN) is proposed by systematically incorporating deep neural networks into a fully parameterized gradient descent scheme and learns an implicit image prior and a universal update rule through recursive supervision.

92 0

Paper Graph

Efficient blind deblurring under high noise levels

J. Anger, M. Delbracio, G. Facciolo•Thu Apr 18 2019

This work shows that current state-of-the-art kernel estimation methods based on the ℓ0 gradient prior can be adapted to handle high noise levels while keeping their efficiency, and shows that a fast non-blind deconvolution method can be significantly improved by first denoising the blurry image.

15 0

Paper Graph

Blind Image Deconvolution using Pretrained Generative Priors

Muhammad Asim, Fahad Shamshad, Ali Ahmed•Mon Aug 19 2019

A modification of the proposed scheme that governs the deblurring process under both generative and classical priors is presented, to improve the performance on rich image datasets not well learned by the generative networks.

7 0

Paper Graph

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

J. Ponce, Thomas Eboli•Thu Jul 02 2020

This work proposes to precondition the Richardson solver using approximate inverse filters of the (known) blur and natural image prior kernels to allow extremely efficient parameter sharing across the image, and leads to significant gains in accuracy and/or speed compared to classical FFT and conjugate-gradient methods.

48 0

Paper Graph

A Simple Local Minimal Intensity Prior and an Improved Algorithm for Blind Image Deblurring

Fei Wen, R. Ying, Yipeng Liu, Peilin Liu, T. Truong•Wed Oct 28 2020

Blind image deblurring is a long standing challenging problem in image processing and low-level vision. Recently, sophisticated priors such as dark channel prior, extreme channel prior, and local maximum gradient prior, have shown promising effectiveness. However, these methods are computationally expensive. Meanwhile, since these priors involved subproblems cannot be solved explicitly, approximate solution is commonly used, which limits the best exploitation of their capability. To address these problems, this work firstly proposes a simplified sparsity prior of local minimal pixels, namely patch-wise minimal pixels (PMP). The PMP of clear images is much more sparse than that of blurred ones, and hence is very effective in discriminating between clear and blurred images. Then, a novel algorithm is designed to efficiently exploit the sparsity of PMP in deblurring. The new algorithm flexibly imposes sparsity inducing on the PMP under the maximum a posterior (MAP) framework rather than directly uses the half quadratic splitting algorithm. By this, it avoids non-rigorous approximation solution in existing algorithms, while being much more computationally efficient. Extensive experiments demonstrate that the proposed algorithm can achieve better practical stability compared with state-of-the-arts. In terms of deblurring quality, robustness and computational efficiency, the new algorithm is superior to state-of-the-arts. Code for reproducing the results of the new method is available at https://github.com/FWen/deblur-pmp.git.

149 0

Paper Graph

Explore Image Deblurring via Blur Kernel Space

A. Tran, Minh Hoai, Phong Tran, Quynh Phung•Thu Dec 31 2020

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.

8 0

Paper Graph

Explore Image Deblurring via Encoded Blur Kernel Space

A. Tran, Minh Hoai, Phong Tran, Quynh Phung•Wed Mar 31 2021

89 0

Paper Graph

Adding a benchmark result helps the community track progress.

Blind Image Deblurring | State-of-the-Art