Perception Driven Texture Generation
This addresses a novel task in computer vision for applications like design and simulation, though it is incremental as it builds on existing adversarial and perceptual methods.
The paper tackles the problem of generating texture images from perceptual descriptions, such as directionality and roughness, by proposing a joint deep network model that combines adversarial training and perceptual feature regression. The results show the method can produce high-quality textures with desired perceptual properties.
This paper investigates a novel task of generating texture images from perceptual descriptions. Previous work on texture generation focused on either synthesis from examples or generation from procedural models. Generating textures from perceptual attributes have not been well studied yet. Meanwhile, perceptual attributes, such as directionality, regularity and roughness are important factors for human observers to describe a texture. In this paper, we propose a joint deep network model that combines adversarial training and perceptual feature regression for texture generation, while only random noise and user-defined perceptual attributes are required as input. In this model, a preliminary trained convolutional neural network is essentially integrated with the adversarial framework, which can drive the generated textures to possess given perceptual attributes. An important aspect of the proposed model is that, if we change one of the input perceptual features, the corresponding appearance of the generated textures will also be changed. We design several experiments to validate the effectiveness of the proposed method. The results show that the proposed method can produce high quality texture images with desired perceptual properties.