Wallpaper Texture Generation and Style Transfer Based on Multi-Label Semantics

Textures contain a wealth of image information and are widely used in various fields such as computer graphics and computer vision. With the development of machine learning, the texture synthesis and generation have been greatly improved. As a very common element in everyday life, wallpapers contain a wealth of texture information, making it difficult to annotate with a simple single label. Moreover, wallpaper designers spend significant time to create different styles of wallpaper. For this purpose, this paper proposes to describe wallpaper texture images by using multi-label semantics. Based on these labels and generative adversarial networks, we present a framework for perception driven wallpaper texture generation and style transfer. In this framework, a perceptual model is trained to recognize whether the wallpapers produced by the generator network are sufficiently realistic and have the attribute designated by given perceptual description; these multi-label semantic attributes are treated as condition variables to generate wallpaper images. The generated wallpaper images can be converted to those with well-known artist styles using CycleGAN. Finally, using the aesthetic evaluation method, the generated wallpaper images are quantitatively measured. The experimental results demonstrate that the proposed method can generate wallpaper textures conforming to human aesthetics and have artistic characteristics.

I. Introduction

Textures can be used to express the features and structural levels of an object’s surface, including rich image feature information, and are therefore widely used in many image processing tasks. The texture within an image refers to the difference in color, pattern, or illumination, causing the image to appear in structure and space with regular or cluttered details. As one type of image, wallpaper images also contain rich textures. People choose beautiful wallpaper to decorate their rooms, which not only enhances the impression of rooms, but also brings visual pleasure.