ChenYuxu4n

Auto_painter

Recently, realistic image generation using deep neural networks has become a hot topic in machine learning and computer vision. Such an image can be generated at pixel level by learning from a large collection of images. Learning to generate colorful cartoon images from black-and-white sketches is not only an interesting research problem, but also a useful application in digital entertainment. In this paper, we investigate the sketch-to-image synthesis problem by using conditional generative adversarial networks (cGAN). We propose a model called auto-painter which can automatically generate compatible colors given a sketch. Wasserstein distance is used in training cGAN to overcome model collapse and enable the model converged much better. The new model is not only capable of painting hand-draw sketch with compatible colors, but also allowing users to indicate preferred colors. Experimental results on different sketch datasets show that the auto-painter performs better than other existing image-to-image methods.

Bayesian_neural_network_papers

Papers for Bayesian-NN

bw2color

deepcolor

Automatic coloring and shading of manga-style lineart, using Tensorflow + cGANs

InfoGAN

Code for reproducing key results in the paper "InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets"

Manga_Colorization

cGAN-based Manga Colorization Using a Single Training Image.

pytorch-book

PyTorch tutorials and fun projects including neural talk, neural style, poem writing, anime generation

PyTorch-GAN

PyTorch implementations of Generative Adversarial Networks.

Style2Paints_V3

Reimplementation of Style2Paints V3

tensorflow-infogan

:dolls: InfoGAN: Interpretable Representation Learning

ChenYuxu4n/Auto_painter

Recently, realistic image generation using deep neural networks has become a hot topic in machine learning and computer vision. Such an image can be generated at pixel level by learning from a large collection of images. Learning to generate colorful cartoon images from black-and-white sketches is not only an interesting research problem, but also a useful application in digital entertainment. In this paper, we investigate the sketch-to-image synthesis problem by using conditional generative adversarial networks (cGAN). We propose a model called auto-painter which can automatically generate compatible colors given a sketch. Wasserstein distance is used in training cGAN to overcome model collapse and enable the model converged much better. The new model is not only capable of painting hand-draw sketch with compatible colors, but also allowing users to indicate preferred colors. Experimental results on different sketch datasets show that the auto-painter performs better than other existing image-to-image methods.

ChenYuxu4n/Bayesian_neural_network_papers

Papers for Bayesian-NN

ChenYuxu4n/bw2color

ChenYuxu4n/deepcolor

Automatic coloring and shading of manga-style lineart, using Tensorflow + cGANs

ChenYuxu4n/InfoGAN

Code for reproducing key results in the paper "InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets"

ChenYuxu4n/Manga_Colorization

cGAN-based Manga Colorization Using a Single Training Image.

ChenYuxu4n/pytorch-book

PyTorch tutorials and fun projects including neural talk, neural style, poem writing, anime generation

ChenYuxu4n/PyTorch-GAN

PyTorch implementations of Generative Adversarial Networks.

ChenYuxu4n/Style2Paints_V3

Reimplementation of Style2Paints V3

ChenYuxu4n/tensorflow-infogan

:dolls: InfoGAN: Interpretable Representation Learning

ChenYuxu4n/tensorflow-vgg

VGG19 and VGG16 on Tensorflow