This project consists of a de-blurring deep learning model, aimed to remove gaussian blur and gaussian noise from images.
The goal is to create a model which, taken a blurred image X, is able to reconstruct the original de-blurred image y.
The dataset is built starting from CIFAR-10 images collection, a Gaussian Blur filter is applied to obtain the blurred images used to train the models.
Two architectures are proposed: AutoEncoder vs. ResNet model.
-
Notifications
You must be signed in to change notification settings - Fork 0
This project consists of a de-blurring deep learning model, aimed to remove gaussian blur and gaussian noise from images. The goal is to create a model which, taken a blurred image X, is able to reconstruct the original de-blurred image y. The dataset is built starting from CIFAR-10 images collection, a Gaussian Blur filter is applied to obtain …
AndreP-git/Gaussian-Deblurring-DNN
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
This project consists of a de-blurring deep learning model, aimed to remove gaussian blur and gaussian noise from images. The goal is to create a model which, taken a blurred image X, is able to reconstruct the original de-blurred image y. The dataset is built starting from CIFAR-10 images collection, a Gaussian Blur filter is applied to obtain …
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published