Comicolorization

Furusawa, Chie; Hiroshiba, Kazuyuki; Ogaki, Keisuke; Odagiri, Yuri

doi:10.1145/3145749.3149430

Cited by 83 publications

(15 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sato et al [26] segmented the target and reference image into different regions, then represented regions as nodes of a graph structure and colorized the monochrome target image by matching the graphs of the target and reference images. Furusawa et al [6] proposed the first semiautomatic system to colorize an entire manga with color features extracted from the input reference image. Chen et al [8] proposed an active learning based framework to match local regions between line arts and reference color image, followed by mixed-integer quadratic programming (MIQP) which considers the spatial contexts to further refine matching results.…”

Section: Line Drawing Colorizationmentioning

confidence: 99%

“…Line drawing colorization is challenging, because line drawings, different from grayscale images [1], [2], [3], [4], only contain structure content composing of a series of lines without any luminance or texture information. This question has greatly attracted attention of researchers in the field of Computer Graphics, therefore many approaches [5], [6], [7], [8] are proposed for mange and cartoon line drawing colorization during the past time.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

AnimeDiffusion: Anime Face Line Drawing Colorization via Diffusion Models

Cao¹,

Meng²,

Mok³

et al. 2023

Preprint

View full text Add to dashboard Cite

It is a time-consuming and tedious work for manually colorizing anime line drawing images, which is an essential stage in cartoon animation creation pipeline. Reference-based line drawing colorization is a challenging task that relies on the precise cross-domain long-range dependency modelling between the line drawing and reference image. Existing learning methods still utilize generative adversarial networks (GANs) as one key module of their model architecture. In this paper, we propose a novel method called AnimeDiffusion using diffusion models that performs anime face line drawing colorization automatically. To the best of our knowledge, this is the first diffusion model tailored for anime content creation. In order to solve the huge training consumption problem of diffusion models, we design a hybrid training strategy, first pre-training a diffusion model with classifier-free guidance and then fine-tuning it with image reconstruction guidance. We find that with a few iterations of fine-tuning, the model shows wonderful colorization performance, as illustrated in Fig. 1. For training AnimeDiffusion, we conduct an anime face line drawing colorization benchmark dataset, which contains 31696 training data and 579 testing data. We hope this dataset can fill the gap of no available high resolution anime face dataset for colorization method evaluation. Through multiple quantitative metrics evaluated on our dataset and a user study, we demonstrate AnimeDiffusion outperforms state-of-the-art GANs-based models for anime face line drawing colorization. We also collaborate with professional artists to test and apply our AnimeDiffusion for their creation work. We release our code on https://github.com/xqmeng/AnimeDiffusion.

show abstract

Section: Line Drawing Colorizationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

AnimeDiffusion: Anime Face Line Drawing Colorization via Diffusion Models

Cao¹,

Meng²,

Mok³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Some researchers have also investigated manga colorization. Furusawa et al [7] made the first attempt to color entire frames of a manga page semiautomatically. Hensman and Aizawa [8] proposed an off-line learning method for manga colorization using a reference image that has been painted.…”

Section: Line Drawing Colorizationmentioning

confidence: 99%

Do You Like Sclera? Sclera-region Detection and Colorization for Anime Character Line Drawings

Aizawa¹,

Sei²,

Yasuyuki³

et al. 2019

IJNDC

View full text Add to dashboard Cite

Colorizing line drawings requires special skill, experience, and knowledge. Artists also spend a great deal of time and effort creating art. Given this background, research on automated line drawing colorization was recently conducted. However, the existing approaches present multiple problems, one of which is the inconsistency of the whites of the eyes (sclera) between line drawings and the results of colorizing. In particular, in line drawings, a person's skin and sclera are often expressed in white. Hence, there are cases in which existing colorization methods cannot predict the boundary correctly. In this study, we propose automated colorization methods that use machine learning to segment sclera regions in grayscale line drawings. To improve the accuracy of previous automated colorization approaches, we implemented sclera-region detection and an automated colorizing approach on grayscale line drawings of people. In addition, we evaluated the colorization results created by our methods through a user study. Statistics show that our methods are somewhat superior to industrial application, but many of our respondents perceived little difference between the methods.

show abstract

“…However, Pix2pix [2], a modified method of GANs, which can generate images based on an input vector, has motivated research into automatic line art colorization. For example, the methods of [3][4][5] give user-guided suggestions about the desired data for colors and locations.…”

Section: Introductionmentioning

confidence: 99%

Seg2pix: Few Shot Training Line Art Colorization with Segmented Image Data

Seo

2021

Applied Sciences

View full text Add to dashboard Cite

There are various challenging issues in automating line art colorization. In this paper, we propose a GAN approach incorporating semantic segmentation image data. Our GAN-based method, named Seg2pix, can automatically generate high quality colorized images, aiming at computerizing one of the most tedious and repetitive jobs performed by coloring workers in the webtoon industry. The network structure of Seg2pix is mostly a modification of the architecture of Pix2pix, which is a convolution-based generative adversarial network for image-to-image translation. Through this method, we can generate high quality colorized images of a particular character with only a few training data. Seg2pix is designed to reproduce a segmented image, which becomes the suggestion data for line art colorization. The segmented image is automatically generated through a generative network with a line art image and a segmentation ground truth. In the next step, this generative network creates a colorized image from the line art and segmented image, which is generated from the former step of the generative network. To summarize, only one line art image is required for testing the generative model, and an original colorized image and segmented image are additionally required as the ground truth for training the model. These generations of the segmented image and colorized image proceed by an end-to-end method sharing the same loss functions. By using this method, we produce better qualitative results for automatic colorization of a particular character’s line art. This improvement can also be measured by quantitative results with Learned Perceptual Image Patch Similarity (LPIPS) comparison. We believe this may help artists exercise their creative expertise mainly in the area where computerization is not yet capable.

show abstract

Comicolorization

Cited by 83 publications

References 6 publications

AnimeDiffusion: Anime Face Line Drawing Colorization via Diffusion Models

AnimeDiffusion: Anime Face Line Drawing Colorization via Diffusion Models

Do You Like Sclera? Sclera-region Detection and Colorization for Anime Character Line Drawings

Seg2pix: Few Shot Training Line Art Colorization with Segmented Image Data

Contact Info

Product

Resources

About