用于肖像素描合成的特征权重学习CycleGAN
首发时间:2019-09-12
摘要:针对现有的肖像素描生成算法得到的图像不够清晰以及局部区域没有素描纹理生成的问题,本文从神经网络结构中通道之间的相互联系出发,提出了基于特征权重学习的循环一致性生成对抗网络(FWL-CycleGAN),以此生成肖像面部细节更加丰富的素描图。此外,为了解决生成图像和真实素描图像之间像素不对齐导致的轮廓模糊的问题,本文提出了特征匹配损失函数,对生成图像和真实图像进行高层次的表达,在高层次的特征空间上对二者进行比较,然后通过结合相邻像素差异平滑loss的方法得到更加清晰的高质量的图像。
关键词: 生成对抗网络 肖像素描 特征权重学习 特征匹配损失函数
For information in English, please click here
Feature Weight Learning CycleGAN for Stylization of Portrait-Sketch Synthesis
Abstract:In order to solve the problem of the generated image obtained by existing portrait-sketch synthesis algorithm which is not clear enough and the local area has less sketch texture, this paper proposes a cycle-consistency GAN based on feature weight learning (FWL-CycleGAN) which makes the interrelationship between channels in the neural network structure, so as to generate a sketch image with more facial details. In addition, for the sake of alleviating the contour blur caused by the pixel-to-pixel unalignment between the prediction and the groundtruth, this paper proposes feature matching loss function to present high-level expressions of generated images and real images for comparison in feature space, and finally produces a high-quality sketch image with a method of smoothing difference between adjacent pixels.
Keywords: Generative Adversarial Networks portrait-sketch feature weight learning feature matching loss function
基金:
引用
No.****
同行评议
勘误表
用于肖像素描合成的特征权重学习CycleGAN
评论
全部评论0/1000