AlphaGAN: Generative adversarial networks for natural image matting [article]

Sebastian Lutz, Konstantinos Amplianitis, Aljosa Smolic
2018 arXiv   pre-print
We present the first generative adversarial network (GAN) for natural image matting. Our novel generator network is trained to predict visually appealing alphas with the addition of the adversarial loss from the discriminator that is trained to classify well-composited images. Further, we improve existing encoder-decoder architectures to better deal with the spatial localization issues inherited in convolutional neural networks (CNN) by using dilated convolutions to capture global context
more » ... ation without downscaling feature maps and losing spatial information. We present state-of-the-art results on the alphamatting online benchmark for the gradient error and give comparable results in others. Our method is particularly well suited for fine structures like hair, which is of great importance in practical matting applications, e.g. in film/TV production.
arXiv:1807.10088v1 fatcat:xeb7v5u2cjh7fhjaisd6t2aloa