MPRNet

Image restoration model

A deep learning model designed to progressively restore degraded images by iteratively refining the degradation and its representation in the image

[CVPR 2021] Multi-Stage Progressive Image Restoration. SOTA results for Image deblurring, deraining, and denoising.

GitHub

1k stars
16 watching
194 forks
Language: Python
last commit: over 2 years ago
computer-visioncvpr-2021cvpr2021cvpr21image-deblurringimage-denoisingimage-derainingimage-restorationlow-level-visionmultistage-networkprogressive-restorationpytorch

Related projects:

RepositoryDescriptionStars
swz30/restormerProposes an efficient neural architecture model for high-resolution image restoration tasks1,845
cszn/srmdDevelops a single convolutional network to handle various image degradations with improved scalability and efficiency427
cszn/ircnnThis project trains deep CNN denoisers to improve image restoration tasks such as deblurring and demosaicking through model-based optimization methods.602
algolzw/daclip-uirThis project controls vision-language models to restore degraded images in various environments and conditions.673
xlearning-scu/2022-cvpr-airnetRestores degraded images by combining multiple tasks of dehazing, denoising and deraining in a single framework176
cszn/dpsrA deep learning-based method to improve image quality by reducing blur effects839
algolzw/image-restoration-sdeImage restoration software using stochastic differential equations593
mc-e/deep-generalized-unfolding-networks-for-image-restorationAn image restoration framework using neural networks with interpretable and adaptive structure for diverse applications136
codeslake/pvdnetAn open-source implementation of a deep learning model for video deblurring and motion estimation.114
hongguangzhang/dmphn-cvpr19-masterAn image deblurring technique utilizing a hierarchical network architecture193
siavashbigdeli/dmspA MATLAB implementation of an image restoration algorithm based on a deep mean-shift prior33
lingyanruan/lakdnetAn image deblurring model that revisits the use of convolutional neural networks to improve efficiency and performance compared to transformers.102
hyeongseokson1/kpacAn implementation of a deep learning model for deblurring images affected by defocus.58
radimspetlik/si-ddpm-fmoA Python-based framework for training and evaluating deep learning models for single-image deblurring, shape, and trajectory recovery of fast-moving objects.5
subeeshvasu/2018_subeesh_nbd_cvprProvides results and tools for image deblurring using CNNs to handle kernel uncertainty5