L-CoDe:Language-Based Colorization Using Color-Object Decoupled Conditions

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 colorobject 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.

Authors

• Shuchen Weng National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University National Engineering Research Center of Visual Technology, School of Computer Science, Peking University
• Hao Wu Beijing Jiaotong University Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence
• Zheng Chang
• Jiajun Tang
• Si Li Beijing University of Posts and Telecommunications
• Boxin Shi Peking University

Keywords

No keywords are indexed for this paper.