AlphaGAN: Generative adversarial networks for natural image matting
Item Type:Conference Paper
Citation:Lutz, S., Aplianitis, K. & Smolic, A., AlphaGAN: Generative adversarial networks for natural image matting, 2018
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 wellcomposited 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 information 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.
Science Foundation Ireland (SFI)
Type of material:Conference Paper
Availability:Full text available