AlphaGAN: Generative adversarial networks for natural image matting
File Type:
PDFItem Type:
Conference PaperDate:
2018Access:
openAccessCitation:
Lutz, S., Aplianitis, K. & Smolic, A., AlphaGAN: Generative adversarial networks for natural image matting, 2018Abstract:
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.
Sponsor
Grant Number
Science Foundation Ireland (SFI)
15/RP/2776
Author's Homepage:
http://people.tcd.ie/smolicaDescription:
PUBLISHEDType of material:
Conference PaperCollections
Availability:
Full text availableSubject (TCD):
Creative Technologies , Multimedia & CreativityMetadata
Show full item recordLicences: