Deep Koalarization: Image Colorization using CNNs and Inception-ResNet-v2

Federico Baldassarre, Diego González Morín, Lucas Rodés-Guirao
12/9/2017
cs.CV

Official code: baldassarreFe/deep-koalarization (414 stars, MIT, TensorFlow, last commit 2022-11-23).

Abstract

We review some of the most recent approaches to colorize gray-scale images using deep learning methods. Inspired by these, we propose a model which combines a deep Convolutional Neural Network trained from scratch with high-level features extracted from the Inception-ResNet-v2 pre-trained model. Thanks to its fully convolutional architecture, our encoder-decoder model can process images of any size and aspect ratio. Other than presenting the training results, we assess the "public acceptance" of the generated images by means of a user study. Finally, we present a carousel of applications on different types of images, such as historical photographs.

View on arXivView PDF

Code Implementations(1)

baldassarreFe/deep-koalarizationOfficial100%
TensorFlowMIT

Keras/Tensorflow implementation of our paper Grayscale Image Colorization using deep CNN and Inception-ResNet-v2 (https://arxiv.org/abs/1712.03400)

41479Shell, PythonMar 28, 20173 years agoMIT
colorizationconvolutional-neural-networksdeep-learninginception-resnetkeras+1 more

Similar Papers

Incorporating Ensemble and Transfer Learning For An End-To-End Auto-Colorized Image Detection Model

87% match2023

Diffusing Colors: Image Colorization with Text Guided Diffusion

86% match2023

SPDGAN: A Generative Adversarial Network based on SPD Manifold Learning for Automatic Image Colorization

85% match2023

Learning Representations for Automatic Colorization

85% match1 repo2202016

Real-Time User-Guided Image Colorization with Learned Deep Priors

84% match1 repo2.7k2017

Automatic Image Colourizer

84% match2023

Cite this paper

@article{baldassarre2017deep,
  title  = {Deep Koalarization: Image Colorization using CNNs and Inception-ResNet-v2},
  author = {Federico Baldassarre and Diego González Morín and Lucas Rodés-Guirao},
  year   = {2017},
  eprint = {1712.03400},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1712.03400}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1712.03400.svg)](https://codeofpaper.com/paper/1712.03400)

Discussion