In order to extract effective representations of data using deep learning models, deep
convolutional activation feature (DeCAF) is usually considered. However, since the deep …

In everyday life we encounter a wide range of liquids (eg, water, custard, toothpaste) with
distinctive optical appearances and viscosities. Optical properties (eg, color, translucency) …

We review recent methods in 2D creative pattern generation and their control mechanisms,
focusing on procedural methods. The review is motivated by an artist's perspective and …

Terrains are visually prominent and commonly needed objects in many computer graphics
applications. While there are many algorithms for synthetic terrain generation, it is rather …

Texture similarity plays important roles in texture analysis and material recognition.
However, perceptually-consistent fine-grained texture similarity prediction is still …

Similarity learning plays a fundamental role in the fields of multimedia retrieval and pattern
recognition. Prediction of perceptual similarity is a challenging task as in most cases we lack …

Procedural textures are normally generated from mathematical models with parameters
carefully selected by experienced users. However, for naive users, the intuitive way to obtain …

In recent years, researchers have proposed many deep learning algorithms for data
representation learning. However, most deep networks require extensive training data and a …

This paper investigates a novel task of generating texture images from perceptual
descriptions. Previous work on texture generation focused on either synthesis from …

Illustrative textures, such as stippling or hatching, were predominantly used as an alternative
to conventional Phong rendering. Recently, the potential of encoding information on …