Restormer
Image restorer
Proposes an efficient neural architecture model for high-resolution image restoration tasks
[CVPR 2022--Oral] Restormer: Efficient Transformer for High-Resolution Image Restoration. SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.
2k stars
18 watching
243 forks
Language: Python
last commit: about 2 years agocvpr2022defocus-deblurringefficient-transformershigh-resolutionimage-deblurringimage-derainingimage-restorationlow-level-visionmotion-deblurringpytorchtransformer
Related projects:
| Repository | Description | Stars |
|---|---|---|
| swz30/mprnet | A deep learning model designed to progressively restore degraded images by iteratively refining the degradation and its representation in the image | 1,197 |
 xlearning-scu/2022-cvpr-airnet | Restores degraded images by combining multiple tasks of dehazing, denoising and deraining in a single framework | 176 |
 algolzw/daclip-uir | This project controls vision-language models to restore degraded images in various environments and conditions. | 673 |
 zzh-tech/bit | Develops a deep learning-based method for deblurring images and videos from motion blur | 225 |
 cszn/ircnn | This project trains deep CNN denoisers to improve image restoration tasks such as deblurring and demosaicking through model-based optimization methods. | 602 |
 zhendongwang6/uformer | An implementation of a deep learning model for restoring images in various conditions | 817 |
 uschmidt83/shrinkage-fields | A collection of MATLAB functions for image restoration and deconvolution using shrinkage fields | 36 |
 lingyanruan/lakdnet | An image deblurring model that revisits the use of convolutional neural networks to improve efficiency and performance compared to transformers. | 102 |
 invokerer/deeprft | Deblurring technique using deep learning and Fourier transformation to remove image blur | 248 |
 codeslake/ifan | Implementation of an algorithm for single image deblurring in images with defocus blur | 228 |
| cszn/srmd | Develops a single convolutional network to handle various image degradations with improved scalability and efficiency | 427 |
| cszn/dpsr | A deep learning-based method to improve image quality by reducing blur effects | 839 |
 chosj95/mimo-unet | Develops a deep learning model for single image deblurring with improved performance and computational efficiency | 382 |
 rozumden/defmo | A deep learning framework for deblurring and recovering the shape of fast-moving objects from blurred images | 171 |
 xl-tang3/uaudeblur | Computes deblurred images from blurry ones using deep residual prior and uncertainty-aware approach | 57 |