Direction-aware Neural Style Transfer with Texture Enhancement

Publication date: Available online 30 August 2019Source: NeurocomputingAuthor(s): Hao Wu, Zhengxing Sun, Yan Zhang, Qian LiAbstractNeural learning methods have been shown to be effective in style transfer. These methods, which are called NST, aim to synthesize a new image that retains the high-level structure of a content image while keeps the low-level features of a style image. However, these models using convolutional structures only extract local statistical features of style images and semantic features of content images. Since the absence of low-level features in the content image, these methods would synthesize images that look unnatural and full of traces of machines. In this paper, we find that direction, that is, the orientation of each painting stroke, can capture the soul of image style preferably and thus generates much more natural and vivid stylizations. According to this observation, we propose a Direction-aware Neural Style Transfer with Texture Enhancement. There are four major innovations. First, we separate the style transfer method into two stage, namely, NST stage and Texture Enhancement stage. Second, for the NST stage, a novel direction field loss is proposed to steer the direction of strokes in the synthesized image. And to build this loss function, we propose novel direction field loss networks to generate and compare the direction fields of content image and synthesized image. By incorporating the direction field loss in neural style transfer, we ob...
Source: Neurocomputing - Category: Neuroscience Source Type: research