L-CoDe:Language-Based Colorization Using Color-Object Decoupled Conditions
Shuchen Weng, Hao Wu, Zheng Chang, Jiajun Tang, Si Li, Boxin Shi
Abstract
Colorizing a grayscale image is inherently an ill-posed problem with multi-modal uncertainty. Language-based colorization offers a natural way of interaction to reduce such uncertainty via a user-provided caption. However, the color-object coupling and mismatch issues make the mapping from word to color difficult. In this paper, we propose L-CoDe, a Language-based Colorization network using color-object Decoupled conditions. A predictor for object-color corresponding matrix (OCCM) and a novel attention transfer module (ATM) are introduced to solve the color-object coupling problem. To deal with color-object mismatch that results in incorrect color-object correspondence, we adopt a soft-gated injection module (SIM). We further present a new dataset containing annotated color-object pairs to provide supervisory signals for resolving the coupling problem. Experimental results show that our approach outperforms state-of-the-art methods conditioned on captions.
BibTeX
@inproceedings{aaai2022_lcodelanguagebas,
title = {L-CoDe:Language-Based Colorization Using Color-Object Decoupled Conditions},
author = {Shuchen Weng and Hao Wu and Zheng Chang and Jiajun Tang and Si Li and Boxin Shi},
booktitle = {AAAI 2022},
year = {2022}
}