TY - GEN
T1 - Enhancing Video Colorization with Deep Learning
T2 - Intelligent Systems Conference, IntelliSys 2024
AU - Stival, Leandro
AU - da Silva Torres, Ricardo
AU - Pedrini, Helio
PY - 2024
Y1 - 2024
N2 - Traditional colorization approaches rely on the expertise of artists or researchers that meticulously paint or digitally add colors to an image (or video frames), which is often a time-consuming, laborious, and error-prone task. Automatic methods, based on deep learning techniques, have replaced such approaches to colorization. Despite the advances toward improving their accuracy, there is no consensus regarding the best training procedures for existing artificial neural network techniques proposed for video colorization. In this paper, in order to fill this gap, we focus on the impact of selecting an appropriate loss function. We investigate seven loss functions to find the combination that gives the best results with Deep Learning Video Colorization (DLVC) using a U-Net topology and an attention mechanism trained on the DAVIS dataset. An investigation of the current validation metrics for colorization results was also conducted to analyze their ability to accurately judge colors between frames.
AB - Traditional colorization approaches rely on the expertise of artists or researchers that meticulously paint or digitally add colors to an image (or video frames), which is often a time-consuming, laborious, and error-prone task. Automatic methods, based on deep learning techniques, have replaced such approaches to colorization. Despite the advances toward improving their accuracy, there is no consensus regarding the best training procedures for existing artificial neural network techniques proposed for video colorization. In this paper, in order to fill this gap, we focus on the impact of selecting an appropriate loss function. We investigate seven loss functions to find the combination that gives the best results with Deep Learning Video Colorization (DLVC) using a U-Net topology and an attention mechanism trained on the DAVIS dataset. An investigation of the current validation metrics for colorization results was also conducted to analyze their ability to accurately judge colors between frames.
KW - Deep learning
KW - Evaluation metrics
KW - Training loss function
KW - Video colorization
U2 - 10.1007/978-3-031-66329-1_32
DO - 10.1007/978-3-031-66329-1_32
M3 - Conference paper
AN - SCOPUS:85200976851
SN - 9783031663284
VL - 1
T3 - Lecture Notes in Networks and Systems
SP - 496
EP - 509
BT - Intelligent Systems and Applications
A2 - Arai, Kohei
PB - Springer
Y2 - 5 September 2024 through 6 September 2024
ER -