Attention-Aware Anime Line Drawing Colorization
This work addresses a domain-specific problem for the animation industry by providing an incremental improvement over existing reference-based methods.
The paper tackles the problem of automatic colorization of anime line drawings by introducing an attention-based model that improves feature extraction and cross-domain dependencies, resulting in outperforming state-of-the-art methods with more accurate line structure and semantic color information.
Automatic colorization of anime line drawing has attracted much attention in recent years since it can substantially benefit the animation industry. User-hint based methods are the mainstream approach for line drawing colorization, while reference-based methods offer a more intuitive approach. Nevertheless, although reference-based methods can improve feature aggregation of the reference image and the line drawing, the colorization results are not compelling in terms of color consistency or semantic correspondence. In this paper, we introduce an attention-based model for anime line drawing colorization, in which a channel-wise and spatial-wise Convolutional Attention module is used to improve the ability of the encoder for feature extraction and key area perception, and a Stop-Gradient Attention module with cross-attention and self-attention is used to tackle the cross-domain long-range dependency problem. Extensive experiments show that our method outperforms other SOTA methods, with more accurate line structure and semantic color information.