Deep image prior regularized by coupled total variation for image colorization

In this repository we provide Jupyter Notebooks to reproduce the results of :

Deep image prior regularized by coupled total variation for image colorization SSVM 2023 Gaetano Agazzotti, Fabien Pierre and Frédéric Sur paper

The code of the following papers have been used and modified:

Colorful Image Colorization ECCV 2016 Richard Zhang, Phillip Isola, Alexei A. Efros Project Page

Deep Image Prior CVPR 2018 Dmitry Ulyanov, Andrea Vedaldi, Victor Lempitsky Project Page

Install

Here is the list of libraries you need to install to execute the code:

• python = 3.7
• jupyter
• matplotlib = 3.3.4
• torch = 1.10.1
• torchvision = 0.11.2
• scikit-image = 0.17.2
• numpy = 1.19.5
• easydict = 1.9

All of them can be installed via pip , e.g.

pip install -r requirements.txt

Citation

@inproceedings{Agazzotti23deep,
author    = {Agazzotti, Gaetano and Pierre, Fabien and Sur, Frédéric},
title     = {Deep image prior regularized by coupled total variation for image colorization},
booktitle   = {Proceedings of Scale Space and Variational Methods in Computer Vision (SSVM)},
year      = {2023}
}