A brief analysis of iColoriT for interactive image colorization.

This paper briefly describes and analyzes iColoriT, a hybrid colorization method based on a Vision Transformer that propagates user hints to relevant regions of a grayscale image while using color priors learned from a large image dataset. This approach gives users more control over color inference...

ver descrição completa

Detalhes bibliográficos
Autores: García, Rosana, Randall, Gregory, Raad, Lara
Formato: artículo
Estado:Versión publicada
Fecha de publicación:2024
País:Uruguay
Recursos:Universidad de la República
Repositorio:COLIBRI
Idioma:inglés
OAI Identifier:oai:colibri.udelar.edu.uy:20.500.12008/43916
Acesso em linha:https://www.ipol.im/pub/art/2024/539/
https://hdl.handle.net/20.500.12008/43916
Access Level:acceso abierto
Palavra-chave:Colorization
Interactive
ViT
Descrição
Resumo:This paper briefly describes and analyzes iColoriT, a hybrid colorization method based on a Vision Transformer that propagates user hints to relevant regions of a grayscale image while using color priors learned from a large image dataset. This approach gives users more control over color inference and shows a quick way to achieve results.