SOTAVerified

Blind Image Deblurring

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

Papers

Showing 2650 of 70 papers

TitleStatusHype
An Improved Optimal Proximal Gradient Algorithm for Non-Blind Image Deblurring0
Blind Image Deblurring: a Review0
Blind Image Deblurring based on Kernel Mixture0
Blind Image Deblurring by Spectral Properties of Convolution Operators0
Blind image deblurring using class-adapted image priors0
Blind Image Deblurring Using Dark Channel Prior0
Residual Expansion Algorithm: Fast and Effective Optimization for Nonconvex Least Squares Problems0
Scale Adaptive Blind Deblurring0
Select Good Regions for Deblurring based on Convolutional Neural Networks0
Self-Paced Kernel Estimation for Robust Blind Image Deblurring0
Self-Supervised Multi-Scale Network for Blind Image Deblurring via Alternating Optimization0
Semi-Blind Image Deblurring Based on Framelet Prior0
Single Image Blind Deblurring Using Multi-Scale Latent Structure Prior0
Unsupervised Blind Image Deblurring Based on Self-Enhancement0
A Comprehensive Survey on Deep Neural Image Deblurring0
FCL-GAN: A Lightweight and Real-Time Baseline for Unsupervised Blind Image Deblurring0
Frequency-Aware Guidance for Blind Image Restoration via Diffusion Models0
Frequency-domain Learning with Kernel Prior for Blind Image Deblurring0
Graph-Based Blind Image Deblurring From a Single Photograph0
Image Restoration from Parametric Transformations using Generative Models0
Kernel Estimation from Salient Structure for Robust Motion Deblurring0
Learning a Discriminative Prior for Blind Image Deblurring0
Learning Collaborative Generation Correction Modules for Blind Image Deblurring and Beyond0
Learning Discriminative Data Fitting Functions for Blind Image Deblurring0
Learning Spatially-Variant MAP Models for Non-Blind Image Deblurring0
Show:102550
← PrevPage 2 of 3Next →

No leaderboard results yet.