https://github.com/nicolasbizzozzero/inpainting
Image inpainting via dictionary learning and sparse representation.
https://github.com/nicolasbizzozzero/inpainting
dictionary-learning image-inpainting inpaint inpainting inpainting-methods lasso machine-learning paper-implementations
Last synced: 7 months ago
JSON representation
Image inpainting via dictionary learning and sparse representation.
- Host: GitHub
- URL: https://github.com/nicolasbizzozzero/inpainting
- Owner: NicolasBizzozzero
- Created: 2018-04-13T23:29:03.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2019-06-05T12:12:59.000Z (over 6 years ago)
- Last Synced: 2025-04-12T06:18:26.557Z (7 months ago)
- Topics: dictionary-learning, image-inpainting, inpaint, inpainting, inpainting-methods, lasso, machine-learning, paper-implementations
- Language: Python
- Homepage:
- Size: 28.3 MB
- Stars: 49
- Watchers: 2
- Forks: 12
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Image inpainting via dictionary learning and sparse representation
This project aims at rebuild "damaged" pictures by learning a sparse representation of non-damaged patch of the image.
## Model
The model is composed of 3 Linear regressions (one per channel) with L1 regularization (aka Lasso).
It encodes the picture to a HSV color model, normalize its pixels between [-1, 1], and learn which sparse combination of pixels can properly rebuild the picture.
## Examples

## TODO
* Implement a CLI.
* Find a better heuristic for patch approximation order.
* Rewrite the model in PyTorch for GPU acceleration.
* Make the linear model a parameter of the Inpainting class.
## Sources
* Bin Shen and Wei Hu and Zhang, Yimin and Zhang, Yu-Jin, Image Inpainting via Sparse Representation Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP ’09)
* Julien Mairal Sparse coding and Dictionnary Learning for Image Analysis INRIA Visual Recognition and Machine Learning Summer School, 2010
* A. Criminisi, P. Perez, K. Toyama Region Filling and Object Removal by Exemplar-Based Image Inpainting IEEE Transaction on Image Processing (Vol 13-9), 2004