TY - JOUR
T1 - Image colorization
T2 - A survey and dataset
AU - Anwar, Saeed
AU - Tahir, Muhammad
AU - Li, Chongyi
AU - Mian, Ajmal
AU - Khan, Fahad Shahbaz
AU - Muzaffar, Abdul Wahab
PY - 2025/2
Y1 - 2025/2
N2 - 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
AB - 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
KW - CNN model classification
KW - Colorization review
KW - Deep learning
KW - Experimental survey
KW - Image colorization
KW - New colorization dataset
UR - https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=uwapure5-25&SrcAuth=WosAPI&KeyUT=WOS:001333951500001&DestLinkType=FullRecord&DestApp=WOS_CPL
U2 - 10.1016/j.inffus.2024.102720
DO - 10.1016/j.inffus.2024.102720
M3 - Article
SN - 1566-2535
VL - 114
JO - Information Fusion
JF - Information Fusion
M1 - 102720
ER -