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.
Abstract (translated)
我们提出了第一个用于自然图像消光的生成对抗网络(GAN)。我们的新型发电机网络经过培训,可以预测视觉上吸引人的α,同时增加来自鉴别器的对抗性损失,该鉴别器经过训练以对良好合成的图像进行分类。此外,我们改进现有的编码器 - 解码器架构,以通过使用扩张的卷积来捕获全局上下文信息而不缩减特征映射和丢失空间信息,从而更好地处理卷积神经网络(CNN)中继承的空间定位问题。我们在梯度误差的alphamatting在线基准测试中提供了最先进的结果,并在其他方面给出了可比较的结果。我们的方法特别适用于头发等精细结构,这在实际的消光应用中非常重要,例如,在电影/电视制作。
URL
https://arxiv.org/abs/1807.10088