search

irfanICMLL / 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.
132 stars 22 forks source link

why pictures tested out are all green? #8

Open huangchenzhao opened 3 years ago

huangchenzhao commented 3 years ago

i have tried two ways in training, one is training directly on the datasets, another is first using pre-trained model offered by the author then training on the datasets. both of them are tested out all green outputs as follows, one is input picture, another is output. can anybody tell me why. thanks a lot. image2-inputs image2-outputs

chenzhao11 commented 3 years ago

what a coincidence, we have similar id and we come across the same problem.Have you solve this problem?

huangchenzhao commented 3 years ago

what a coincidence, we have similar id and we come across the same problem.Have you solve this problem?

sorry, I have tried but didn't solve this problem...By the way, what a nice coincidence