Cartoon your image
What’s
New: Cartoon image generation using AI namely
using Convolutional Neural Network and Generative Adversarial Network.
Key
Insight: Cartoons
are an artistic form widely used in our daily life. In addition to artistic
interests, their applications range from publication in printed media to
storytelling for children’s education. Like other forms of artworks, many
famous cartoon images were created based on real-world scenes. Figure shows a
real-world scene whose cor-responding cartoon image appeared in the animated
film. However, manually recreating real-world scenes in cartoon styles is very
laborious and involves substantial artistic skills. To obtain high-quality
cartoons, artists have to draw every single line and shade each color region of
target scenes.
Such tools also provide a useful addition to photo editing software such as Instagram and Photoshop.
How it
works: Convolutional
Neural Networks (CNNs) have received considerable attention for solving many
computer vision problem. Given a style image and a content image, Gatys first
proposed a neural style transfer (NST) method based on CNNs that transfers the
style from the style image to the content image, An alternative, promising
approach to image synthesis is to use Generative Adversarial Networks (GANs)
which produce state-of-the-art results in many applications such as text to
image translation image inpainting, image super-resolution etc. The key idea of
a GAN model is to train two networks (i.e., a generator and a discriminator)
iteratively, whereby the adversarial loss provided by the discriminator pushes
the generated images towards the target manifold.
Why it
matters: Meanwhile,
existing image editing software/algorithms with standard features cannot
produce satisfactory results for cartoonization. Therefore, specially designed
techniques that can automatically transform realworld photos to high-quality
cartoon style images are very helpful and for artists, tremendous amount of
time can be saved so that they can focus on more creative work.
Comments
Post a Comment