Revisiting Global Statistics Aggregation for Improving Image Restoration

megvii-research/tlsc 8 Dec 2021

This paper first shows that statistics aggregated on the patches-based/entire-image-based feature in the training/testing phase respectively may distribute very differently and lead to performance degradation in image restorers.

Group-based Sparse Representation for Image Restoration

jianzhangcs/GSR 14 May 2014

In this paper, instead of using patch as the basic unit of sparse representation, we exploit the concept of group as the basic unit of sparse representation, which is composed of nonlocal patches with similar structures, and establish a novel sparse representation modeling of natural images, called group-based sparse representation (GSR).

Class-specific image deblurring

saeed-anwar/Class_Specific_Deblurring IEEE International Conference on Computer Vision (ICCV) 2015

In image deblurring, a fundamental problem is that the blur kernel suppresses a number of spatial frequencies that are difficult to recover reliably.

Patch-Ordering as a Regularization for Inverse Problems in Image Processing

grishavak/Patch_Ordering_as_a_Regularization_for_Inverse_Problems_in_Image_Processing 26 Feb 2016

Recent work in image processing suggests that operating on (overlapping) patches in an image may lead to state-of-the-art results.

Deep Video Deblurring

susomena/DeepSlowMotion 25 Nov 2016

We show that the features learned from this dataset extend to deblurring motion blur that arises due to camera shake in a wide range of videos, and compare the quality of results to a number of other baselines.

On-Demand Learning for Deep Image Restoration

rhgao/on-demand-learning ICCV 2017

While machine learning approaches to image restoration offer great promise, current methods risk training models fixated on performing well only for image corruption of a particular level of difficulty---such as a certain level of noise or blur.

Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring

SeungjunNah/DeepDeblur-PyTorch CVPR 2017

To remove these complicated motion blurs, conventional energy optimization based methods rely on simple assumptions such that blur kernel is partially uniform or locally linear.

Deep Video Deblurring for Hand-Held Cameras

shuochsu/DeepVideoDeblurring CVPR 2017

We show that the features learned from this dataset extend to deblurring motion blur that arises due to camera shake in a wide range of videos, and compare the quality of results to a number of other baselines.

Image Restoration by Iterative Denoising and Backward Projections

tomtirer/IDBP 18 Oct 2017

In this work, we propose an alternative method for solving inverse problems using off-the-shelf denoisers, which requires less parameter tuning.

Blind Image Deconvolution using Deep Generative Priors

axium/Blind-Image-Deconvolution-using-Deep-Generative-Priors 12 Feb 2018

This paper proposes a novel approach to regularize the \textit{ill-posed} and \textit{non-linear} blind image deconvolution (blind deblurring) using deep generative networks as priors.