JP7675367B2 - Image coloring method and device, colored image generation model generating device, and program - Google Patents

Description

The present invention relates to a technology for coloring achromatic monochrome images such as manga.

Traditionally, manga are often created as achromatic monochrome images. However, in recent years, there has been a demand for colored manga in addition to monochrome manga. For this reason, there is an increasing demand for post-coloring of already completed manga consisting of monochrome images. Since performing such coloring processing manually is very costly and time-consuming, systems have been developed that perform automatic or semi-automatic coloring of monochrome images. One such type of coloring processing is described in Non-Patent Document 1, for example.

The technique described in Non-Patent Document 1 performs coloring using machine learning based on an image generation algorithm called Pix2Pix, and in particular adds color hint information provided by the user in addition to a line drawing image as input information.

Lvmin Zhang, Chengze Li, Tien-Tsin Wong, Yi Ji, and Chunping Liu, “Two-stage sketch colorization,” ACM Transactions on Graphics, vol. 37, no. 6, pp. 261:1-261:14, 2018. Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A Efros, “Image-to-image translation with conditional adversarial networks,” CVPR, pp. 5967-5976, 2017.

However, the method described in Non-Patent Document 1 had the problem that it was not accurate enough for coloring manga. This problem is explained below.

The technique described in Non-Patent Document 1 requires prior learning using a large amount of training data, which inevitably means that works from multiple authors are used as training data. However, not only do manga styles vary greatly depending on the author, but even the same author's style can differ depending on the work and the time of production. This makes it difficult to carry out learning appropriate for a specific manga, and therefore poses the problem of difficulty in improving coloring accuracy.

Manga is not composed of line drawings alone, but generally includes shading and other representations that express shading, color, or texture using achromatic patterns or shades. In paper media, these shading and other representations are formed by attaching a template called a "screen tone" to the line drawing. However, in the case of manga that includes shading and other representations described in Non-Patent Document 1, the position of the shading and other representations cannot be specified during the learning stage or coloring process stage. For this reason, it is difficult to represent the shading and other representations in the output results with shading, color, and texture that are appropriate for the shading and other representations, and therefore there is a problem in that it is difficult to improve coloring accuracy.

The present invention has been made in consideration of the above circumstances, and its purpose is to provide an image coloring method and device capable of appropriately coloring achromatic monochrome images, a device for generating a colored image generation model, and a program.

In order to achieve the above object, the image coloring method according to the present invention is characterized by comprising: a model generation step in which a computer generates a colored image generation model that generates the colored image from the monochrome image and the solid image by machine learning using as learning data an achromatic monochrome image, a solid image in which a predetermined coloring area corresponding to the monochrome image is colored with a single color, and a colored image corresponding to the monochrome image; and a colored image generation step in which a colored image that is the corresponding colored image that is the target monochrome image is generated based on the generated colored image generation model, a target monochrome image that is the monochrome image to be colored, and a corresponding solid image that is the solid image and corresponds to the target monochrome image.

The image coloring device according to the present invention is characterized by comprising: a model generation unit that generates a colored image generation model that generates the colored image from the monochrome image and the solid image by machine learning using as learning data an achromatic monochrome image, a solid image in which a single color is applied to a predetermined colored area corresponding to the monochrome image, and a colored image corresponding to the monochrome image; and a coloring processing unit that generates the colored image, which is the corresponding colored image corresponding to the target monochrome image, based on the colored image generation model generated by the model generation unit, a target monochrome image that is the monochrome image to be colored, and a corresponding solid image that is the solid image and corresponds to the target monochrome image.

The image coloring device according to the present invention is characterized in that it includes a colored image generation model that is generated by machine learning using as learning data an achromatic monochrome image, a solid image in which a predetermined coloring area corresponding to the monochrome image is colored with a single color, and a colored image corresponding to the monochrome image, and that generates the colored image from the monochrome image and the solid image, and a coloring processing unit that generates the colored image, which is the corresponding colored image corresponding to the target monochrome image, based on the colored image generation model, a target monochrome image that is the monochrome image to be colored, and a corresponding solid image that is the solid image and corresponds to the target monochrome image.

The colored image generation model generating device according to the present invention is characterized by comprising a model generating unit that generates a colored image generation model that generates a colored image from a monochrome image and a solid image by machine learning using, as training data, an achromatic monochrome image, a solid image in which a single color is applied to a predetermined colored area corresponding to the monochrome image, and a colored image corresponding to the monochrome image.

According to the present invention, a colored image generation model is generated by machine learning using as training data an achromatic monochrome image, a solid image in which a predetermined colored area corresponding to the monochrome image is colored with a single color and does not include the monochrome image, and a colored image corresponding to the monochrome image. That is, since a solid image containing information on the position and color of the coloring target is used for machine learning, the accuracy of the position and color of the coloring for the target monochrome image is improved. That is, the present invention enables appropriate coloring. Furthermore, since a colored image generation model can be created by simply preparing a small amount of training data (a combination of a monochrome image, a solid image, and a colored image), not only is the effort required for creating training data reduced, but coloring that matches the work and the style of the artist becomes possible.

As mentioned above, the present invention requires a solid image. However, the solid image can be easily derived from a monochrome image by hand or with an image processing device without the need for highly specialized skills or knowledge. Therefore, the present invention enables easy and appropriate coloring without the need for highly specialized skills or knowledge.

Functional block diagram of an image coloring device according to a first embodiment FIG. 1 is a diagram showing an example of a monochrome image. FIG. 13 is a diagram showing an example of a solid image. FIG. 1 is a diagram showing an example of a colored image. FIG. 1 is a diagram illustrating the first stage of the learning process. FIG. 2 is a diagram illustrating the second stage of the learning process. Flowchart for explaining the operation of the image coloring device FIG. 13 is a diagram showing an example of a coloring process. Functional block diagram of an image coloring device according to a second embodiment An example of the color hint creation screen

(First embodiment)
An image coloring device according to a first embodiment of the present invention will be described with reference to the drawings. Fig. 1 is a functional block diagram of the image coloring device according to the first embodiment, Fig. 2 is a diagram showing an example of a monochrome image, Fig. 3 is a diagram showing an example of a solid-colored image, and Fig. 4 is a diagram showing an example of a colored image. In this application, "Nekodama", a work by author "Ebi Fry" included in the Manga109-s data set, is used as an image sample.

The image coloring device 100 according to this embodiment generates a colored image generation model that generates the colored image 30 from the monochrome image 10 and the solid image 20 by machine learning using as learning data an achromatic monochrome image 10, a solid image 20 in which a single color is applied to a predetermined colored area corresponding to the monochrome image 10 and does not include the monochrome image 10, and a colored image 30 corresponding to the monochrome image 10.

The image coloring device 100 is a device that generates a colored image 30, which is a corresponding colored image 30a corresponding to the target monochrome image 10, based on a target monochrome image 10a, which is a monochrome image 10 to be colored, and a corresponding solid image 20a, which is a solid image 20 and corresponds to the target monochrome image 10. Each image 10, 10a, 20, 20a, 30, 30a is made up of digital data of any file format, resolution, and depth.

The monochrome image 10 includes a target monochrome image 10a. In other words, the target monochrome image 10a is one of the monochrome images 10, and is input to the image coloring device 100 as a target for coloring processing.

The monochrome image 10 refers to an achromatic image. Here, the monochrome image 10 may be black and white binary digital data, or grayscale digital data. In this embodiment, the monochrome image 10 is composed of digital data obtained by scanning a manga at a specified resolution, or digital data created by a computer in a style equivalent to the monochrome image 10 obtained by scanning a manga.

As shown in FIG. 2, a monochrome manga image 10 includes an achromatic line drawing portion 11 and a shading portion 12 that expresses shading, color, or texture using achromatic patterns or shades.

The line drawing portion 11 is an area drawn with a pen or brush on paper media, and is mainly a monochrome image with strong contrast. That is, the line drawing portion 11 is essentially mainly a black and white binary image. The line drawing portion 11 may be drawn in mid-tone gray. Furthermore, in the monochrome image 10 as digital data, the line drawing portion 11 may contain mid-tone gray pixels so that the black and white binary line drawing is smooth. In the example of Figure 2, the line drawing portion 11 is the area that expresses the contours and edges of each part of the body, such as the face, hands, body, clothes, and accessories.

The shading and other expression section 12 can be formed by pasting a template called "screen tone" on paper media. Screen tone is a technique that allows the expression of intermediate gradations to be expressed in a pseudo manner using continuous patterns such as fine black and white binary dots, patterns, and lines. The shading and other expression section 12 may include intermediate gradation gray. The shading and other expression section 12 can also be formed by hand so as to obtain an effect equivalent to that of a screen tone. In the example of FIG. 2, the shading and other expression section 12 is the area that expresses the shading of the skin under the chin and under the armpits, the color and texture of the hair, and the color and texture of the clothes. In the monochrome image 10 as digital data, the shading and other expression section 12 may include intermediate gradation gray pixels so that the black and white binary pattern becomes smooth. Depending on the resolution of the image data, the shading and other expression section 12 may be substantially a collection of intermediate gradation gray pixels in the monochrome image 10 as digital data.

The solid-color image 20 includes a corresponding solid-color image 20a. In other words, the corresponding solid-color image 20a is one of the solid-color images 20, and is input to the image coloring device 100 as a pair with the target monochrome image 10a in the coloring process.

The solid image 20 is an image that corresponds to the monochrome image 10. The solid image 20 is an image that indicates the color and position (area) for coloring the corresponding monochrome image 10. The solid image 20 is generated manually or by a computer based on the corresponding monochrome image 10. In this embodiment, a solid image 20 generated manually is used.

Figure 3 is an example of a solid-color image corresponding to the monochrome image 10 illustrated in Figure 2. As shown in Figure 3, the solid-color image 20 has a predetermined colored region 21 colored with a single arbitrary color. The solid-color image 20 may include multiple colored regions 21. In this case, the multiple colored regions 21 may be adjacent to each other or may be separated from each other. In this embodiment, the solid-color image 20 corresponds to the monochrome image 10, but does not include the monochrome image 10. The colored region 21 includes a region corresponding to the shading and the like representation portion 12 in the corresponding monochrome image 10. In the example of Figure 3, the colored region 21 from the face to the neck includes a region corresponding to the shading and the like representation portion 12 formed under the chin in Figure 2.

The colored image 30 includes a corresponding colored image 30a. That is, the corresponding colored image 30a is one of the colored images 30, and is output from the image coloring device 100 by a coloring process that uses the target monochrome image 10a and the corresponding solid image 20a as inputs. The colored image 30 used as one of the input images in the learning process of the image coloring device 100 is generated manually based on the corresponding monochrome image 10 and solid image 20. The colored image 30 used in this learning process corresponds to the "ground truth" in the learning process.

Figure 4 is an example of a colored image corresponding to the monochrome image 10 illustrated in Figure 2 and the solid-color image 20 illustrated in Figure 3. As shown in Figure 4, the colored image 30 may be colored in a color different from the color applied to the colored area 21 containing the shading portion 12 in the solid-color image 20 in the area corresponding to the shading portion 12 in the monochrome image 10. In other words, since the monochrome image 10 is achromatic, the shading portion 12 is formed of achromatic patterns or shades to express shadows, colors, or textures, but in the colored image 30, this expression is replaced with an expression using color.

Next, the image coloring device 100 will be described in detail. As shown in FIG. 1, the image coloring device 100 includes a learning processing unit 110, a colored image generation processing unit 120, and a colored image generation model 130.

The image coloring device 100 is composed of a conventionally known computer equipped with a main processing unit, a main memory device, an auxiliary memory device, an input device, a display device, a network device, etc. Each part of the image coloring device 100 can be configured by installing a program on the computer. There is no restriction on the implementation form of the image coloring device 100. For example, the image coloring device 100 can be distributed and implemented on multiple devices.

The learning processing unit 110 generates a colored image generation model 130 that generates a colored image 30 from the monochrome image 10 and the solid image 20 by machine learning using the monochrome image 10, the solid image 20 corresponding to the monochrome image 10, and the colored image 30 corresponding to the monochrome image 10 and the solid image 20 as learning data. Each of the images 10, 20, and 30 may be stored in advance in a predetermined storage device, may be obtained from a predetermined external storage medium, or may be obtained from another device via a network.

The colored image generation processing unit 120 generates a colored image 30, which is a corresponding colored image 30a corresponding to the target monochrome image 10a, based on the generated colored image generation model 130, a target monochrome image 10a which is a monochrome image 10 to be colored, and a corresponding solid image 20a which is a solid image 20 and corresponds to the target monochrome image 10a. The target monochrome image 10a and the corresponding solid image 20a may be stored in advance in a predetermined storage device of the device itself, may be acquired from a predetermined external storage medium, or may be acquired from another device via a network. The colored image generation processing unit 120 can output the generated corresponding colored image 30a to its own display device, to its own predetermined storage device, to a predetermined external storage medium, or to another device via a network.

The colored image generation model 130 is composed of a generative adversarial network. The substance of the colored image generation model 130 is composed of a program stored in a predetermined storage device of the image coloring device 100 and various parameters used by the program and changed by the learning process. The configuration of the colored image generation model 130 and the processing of the learning processing unit 110 will be described in detail below with reference to Figures 5 and 6. Figure 5 is a diagram explaining the first stage of learning, and Figure 6 is a diagram explaining the second stage of learning.

The colored image generation model 130 has two generators (generative networks). The first generator converts the colored image 30 into a monochrome image 10, as shown in FIG. 5. Meanwhile, the second generator generates the colored image 30 from a set of the monochrome image 10 and the solid image 20, as shown in FIG. 6. These two generators are trained separately. Here, the stage of converting the colored image 30 into the monochrome image 10 is called the first stage. Also, the stage of generating the colored image 30 from the set of the monochrome image 10 and the solid image 20 is called the second stage.

The training data consists of a set (x, y, z) of a colored image 30, a monochrome image 20, and a solid image 20. In the first stage, the generator G _A learns how to generate a monochrome image 10 from the colored image 30. This process removes color information from the colored image 30 and predicts the position and pattern of the corresponding monochrome image 10. As shown in FIG. 4, the colored image 30 contains enough information to predict the monochrome image 10. This learning process is similar to the process in Pix2Pix. For details about the process in Pix2Pix, see Non-Patent Document 2.

[First Stage]
In this embodiment, the UNet architecture is applied to the generator G _A. If the colored image 30 is x and the monochrome image 10 is y, the discriminative loss of the generator G _A is expressed by the following equation (1).

Here, the generator G _A learns how to fool the discriminator (identification network) D _A. Meanwhile, the discriminator D _A learns to distinguish between fakes and real objects. In addition to the loss function of the above formula (1), this embodiment uses a loss based on the _L1 distance between the correct monochrome image y and the generated image G _A (x), as shown in the following formula (2).

The final goal of the generator G _A is expressed by the following equation (3).

[Second Stage]
After the first stage, we move to the second stage. In the second stage, a pair of a solid image 20 and a monochrome image 10 is input. The generator G _B learns how to generate a colored image 30 from the solid image 20 and the monochrome image 10. The generative model is an extension of UNet. To obtain one output from two inputs, the model has a two-stream structure.

Let x be the colored image 30, y be the monochrome image 10, and z be the solid image 20. The loss function of the generator G _B is expressed by the following equation (4).

Here, the generator G _B learns how to fool the discriminator (classification network) D _B. Meanwhile, the discriminator D _A learns to classify fakes and real objects. In this embodiment, a loss based on the _L1 distance is used to improve the quality (accuracy) of the output, as shown in the following formula (5).

Furthermore, to maintain cycle consistency, the colored image 30 generated by the generator G _B is input to the trained generator G _A. The _L1 distance between the false monochrome image from the trained generator G _A and the correct monochrome image is calculated (the second term in the following equation (6)). The final goal of the generator G _B is as shown in the following equation (6).

As described above, in the colored image generation model 130 according to the present embodiment, in the second stage, the learning process is performed using the colored image 30 generated by the generator G _B as an input and also using the monochrome image generated by the trained generator G _A.

The colored image generation processing unit 120 generates a corresponding colored image 30a from a target monochrome image 10a and a corresponding solid image 20a using a trained generator G _B.

Next, the operation of the image coloring device 100 according to this embodiment will be described with reference to the flowchart in FIG.

First, the image coloring device 100 performs a learning process using learning data consisting of a monochrome image 10, a solid image 20, and a colored image 30 to generate a colored image generation model 130 (step S1). Next, the image coloring device 100 acquires a monochrome image 10a to be processed and a corresponding solid image 20a corresponding to the monochrome image 10a (steps S2 and S3), and generates a corresponding colored image 30a using the colored image generation model 130 (step S4).

Fig. 8 shows an example of coloring processing by the image coloring device 100 according to the present embodiment. In this example, 10 pages were randomly selected from the above-mentioned work "Nekodama", 5 pages were used for learning processing, and the other 5 pages were used as the coloring target. Note that the example of Fig. 8 shows an image to be compared using a colored image generation model in which the processing of the first stage and the processing of the generator G _A in the second stage are omitted from the colored image generation model 130 according to the present embodiment.

As shown in FIG. 8, with the image coloring device 100 according to this embodiment, it was confirmed that the output image, the corresponding colored image 30a, is extremely similar to the correct colored image 30, and that the coloring accuracy is high. In particular, with the image coloring device 100 according to this embodiment, it was confirmed that high coloring accuracy can be obtained even with a learning process using a small amount of learning data, and that the coloring of the shading and other representation unit 12 is appropriate.

According to such an image coloring device 100, a colored image generation model is generated by machine learning using an achromatic monochrome image 10, a solid image 20 in which a predetermined coloring area corresponding to the monochrome image 10 is colored with a single color and does not include the monochrome image 10, and a colored image 30 corresponding to the monochrome image 10 as learning data. In other words, since the solid image 20, which contains information on the position and color of the coloring target, is used for machine learning, the accuracy of the coloring position and color for the target monochrome image 10a is improved. In other words, the present invention enables appropriate coloring.

As described above, the present invention requires a solid-color image 20. However, the solid-color image 20 can be easily derived from the monochrome image 10 by hand or by an image processing device without the need for highly specialized skills or knowledge. Therefore, the present invention enables easy and appropriate coloring without the need for highly specialized skills or knowledge.

Second Embodiment
An image coloring device according to a second embodiment of the present invention will be described with reference to the drawings. Fig. 9 is a functional block diagram of the image coloring device according to the second embodiment, and Fig. 10 shows an example of a color hint creation screen.

The image coloring device of this embodiment differs from the first embodiment in the method of creating the solid image 20. That is, in the first embodiment, the solid image 20 was created manually from the corresponding monochrome image 10, but in this embodiment, it is created from the monochrome image 10 in the image coloring device 100'. All other points are the same as in the first embodiment, so only the differences will be explained here.

The image coloring device 100' according to the present embodiment includes a solid image generating unit 140, as shown in FIG. 9. The solid image generating unit 140 generates a solid image 20 corresponding to the monochrome image 10 from the monochrome image 10. More specifically, as shown in FIG. 10, the solid image generating unit 140 outputs the monochrome image 10 to a predetermined display device (not shown) and accepts input of one or more color hints 141 from a user. The color hint 141 indicates color information and position information within the image. The solid image generating unit 140 superimposes and displays the input color hint 141 on the monochrome image 10 in a predetermined display form. In the example of FIG. 10, the color hint 141 is displayed as a circular mark having a color. Based on the position information of the input color hint 141, the solid image generating unit 140 searches for a closed area in the monochrome image 10 with the line drawing portion 11 as a boundary, and generates a solid image 20 by coloring the closed area with the color of the color hint as a coloring area. Various conventionally known algorithms for searching for a closed area can be used. The solid image generating unit 140 can store the generated solid image 20 in a specified storage device or an external storage device, or transmit it to an external device.

With this image coloring device 100', the solid image 20 can be generated semi-automatically, improving the efficiency of the coloring process. Other functions and effects are the same as those of the first embodiment.

Although one embodiment of the present invention has been described in detail above, the present invention is not limited to the above embodiment, and various improvements and modifications may be made without departing from the spirit and scope of the present invention.

For example, in the above embodiment, the monochrome image 10 on which the shadow representation portion 12 is formed by a screen or the like is the subject of coloring, but the present invention can also be applied to a monochrome image 10 on which the shadow representation portion 12 is not formed.

In addition, in the above embodiment, the solid image 20 corresponds to the monochrome image 10 but does not include the monochrome image 10 itself, but it may include part or all of the corresponding monochrome image 10.

In addition, in the above embodiment, a generative adversarial network is used as the colored image generation model 130, but the present invention can be applied to other models. For example, the present invention can be applied to a convolutional neural network that receives a solid image and a monochrome image as input and outputs a colored image.

In addition, in the above embodiment, the learning processing unit 110 that generates the colored image generation model 130 and the colored image generation unit 120 that generates the corresponding colored image 30a using the colored image generation model 130 are implemented in the same device, but they may be distributed and implemented in different devices. In this case, the colored image generation model 130 generated by the learning processing unit 110 may be transferred and implemented from the device in which the learning processing unit 110 is implemented to the device in which the colored image generation unit 120 is implemented. This allows the generation process of the colored image generation model 130 and the coloring process by the colored image generation model 130 to be performed independently by different people, at different places, and at different times, thereby improving convenience.

REFERENCE SIGNS LIST 10 monochrome image 10a target monochrome image 20 solid image 20a corresponding solid image 30 colored image 30a corresponding colored image 100, 100' image coloring device 110 learning processing unit 120 colored image generation processing unit 130 colored image generation model 140 solid image generation unit

Claims (10)

The computer
a model generation step of generating a colored image generation model that generates the colored image from the monochrome image and the solid image by machine learning using, as learning data, an achromatic monochrome image, a solid image in which a predetermined colored region corresponding to the monochrome image is colored with a single color, and a colored image corresponding to the monochrome image;
and a colored image generation step of generating a corresponding colored image which is a colored image and corresponds to the target monochrome image based on the generated colored image generation model, a target monochrome image which is the monochrome image to be colored, and a corresponding solid image which is the solid image and corresponds to the target monochrome image. the monochrome image includes an achromatic line drawing portion and a shading or other representation portion that represents shading, color, or texture by an achromatic pattern or shading,
2. The image coloring method according to claim 1, wherein the colored area of the solid-color image includes an area corresponding to the portion expressing shading or the like. The image coloring method according to claim 2, characterized in that the colored image is colored in a color different from a color applied to a colored area including the shading or other representation in the solid image in an area corresponding to the shading or other representation in the monochrome image. The image coloring method according to any one of claims 1 to 3, wherein the colored image generation model is a generative adversarial network. The colored image generation model is
A first generative adversarial network including a first generative network that generates the monochrome image based on the colored image, and a first discrimination network that performs authenticity determination based on the colored image input to the first generative network and the monochrome image generated by the first generative network;
a second generative adversarial network including a second generative network that generates the colored image based on the solid image and the monochrome image, and a second discrimination network that performs authenticity determination based on the colored image generated by the second generative network and the solid image and the monochrome image input to the second generative network;
The model generation step includes a training step of the first generative adversarial network and a training step of the second generative adversarial network,
In the learning step of the second generative adversarial network, in addition to the colored image generated by the second generative network and the solid image and monochrome image input to the second generative network, a learning process is performed using the monochrome image generated by the first generative network that has been trained using the colored image generated by the second generative network as an input,
5. The image coloring method according to claim 4, wherein in the colored image generating step, the corresponding colored image is generated from the target monochrome image and the corresponding solid image using a second generative network of the second generative adversarial network that has been trained. a model generation unit that generates a colored image generation model that generates the colored image from the monochrome image and the solid image by machine learning using, as learning data, an achromatic monochrome image, a solid image in which a predetermined colored region corresponding to the monochrome image is colored with a single color, and a colored image corresponding to the monochrome image;
an image coloring device comprising: a coloring processing unit that generates a corresponding colored image, which is the colored image and corresponds to the target monochrome image, based on a colored image generation model generated by the model generation unit, a target monochrome image, which is the monochrome image to be colored, and a corresponding solid image, which is the solid image and corresponds to the target monochrome image. a colored image generation model that is generated by machine learning using, as learning data, an achromatic monochrome image, a solid-color image in which a predetermined colored region corresponding to the monochrome image is colored with a single color, and a colored image corresponding to the monochrome image, and that generates the colored image from the monochrome image and the solid-color image;
an image coloring device comprising: a coloring processing unit that generates the corresponding colored image, which is the colored image and corresponds to the target monochrome image, based on the colored image generation model, a target monochrome image, which is the monochrome image to be colored, and a corresponding solid image, which is the solid image and corresponds to the target monochrome image. A colored image generation model generating device comprising: a model generation unit that generates a colored image generation model that generates a colored image from a monochrome image and the solid image by machine learning using, as learning data, an achromatic monochrome image, a solid image in which a predetermined colored region corresponding to the monochrome image is colored with a single color, and a colored image corresponding to the monochrome image. A program that causes a computer to function as the image coloring device according to claim 6 or 7. A program that causes a computer to function as a generating device for a colored image generation model according to claim 8.

Images