AlphaGAN: Generative adversarial networks for natural image matting

Abstract

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 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.

arXiv commentAccepted at BMVC 2018

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• Generative Visual Manipulation on the Natural Image Manifold
• Fast Deep Matting for Portrait Animation on Mobile Phone

Cited by in corpus (9)

• Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation
• Convolution-Weight-Distribution Assumption: Rethinking the Criteria of Channel Pruning
• Boosting Semantic Human Matting with Coarse Annotations
• Generate High Resolution Images With Generative Variational Autoencoder
• Medical Matting: A New Perspective on Medical Segmentation with Uncertainty
• On The Utility of Conditional Generation Based Mutual Information for Characterizing Adversarial Subspaces
• A Generative Adversarial Framework for Optimizing Image Matting and Harmonization Simultaneously