Image Colorization: A Survey and Dataset

TL;DR

This paper provides a comprehensive survey of deep learning-based image colorization techniques, introduces a new dataset, and evaluates existing methods to guide future research in the field.

Contribution

It systematically categorizes colorization methods, introduces a new dataset, and offers extensive experimental evaluation and analysis of current techniques.

Findings

Existing datasets have limitations that affect evaluation.

The new dataset improves benchmarking for colorization methods.

Evaluation results highlight strengths and weaknesses of current approaches.

Abstract

Image colorization estimates RGB colors for grayscale images or video frames to improve their aesthetic and perceptual quality. Over the last decade, deep learning techniques for image colorization have significantly progressed, necessitating a systematic survey and benchmarking of these techniques. This article presents a comprehensive survey of recent state-of-the-art deep learning-based image colorization techniques, describing their fundamental block architectures, inputs, optimizers, loss functions, training protocols, training data, etc. It categorizes the existing colorization techniques into seven classes and discusses important factors governing their performance, such as benchmark datasets and evaluation metrics. We highlight the limitations of existing datasets and introduce a new dataset specific to colorization. We perform an extensive experimental evaluation of existing image colorization methods using both existing datasets and our proposed one. Finally, we discuss the limitations of existing methods and recommend possible solutions and future research directions for this rapidly evolving topic of deep image colorization. The dataset and codes for evaluation are publicly available at https://github.com/saeed-anwar/ColorSurvey.