The seminal work of Gatys et al. demonstrated the power of Convolutional Neural Networks
(CNNs) in creating artistic imagery by separating and recombining image content and style …

Terrains are a crucial component of three‐dimensional scenes and are present in many
Computer Graphics applications. Terrain modeling methods focus on capturing landforms in …

Here we introduce a new model of natural textures based on the feature spaces of
convolutional neural networks optimised for object recognition. Samples from the model are …

Abstract We present TexFusion (Texture Diffusion), a new method to synthesize textures for
given 3D geometries, using only large-scale text-guided image diffusion models. In contrast …

Thoroughly revised, this third edition focuses on modern techniques used to generate
synthetic three-dimensional images in a fraction of a second. With the advent of …

It is ubiquitous that meaningful structures are formed by or appear over textured surfaces.
Extracting them under the complication of texture patterns, which could be regular, near …

Porous structures such as trabecular bone are widely seen in nature. These structures are
lightweight and exhibit strong mechanical properties. In this paper, we present a method to …

This survey explores procedural content generation via machine learning (PCGML), defined
as the generation of game content using machine learning models trained on existing …

We present a mobile vision system for multi-person tracking in busy environments.
Specifically, the system integrates continuous visual odometry computation with tracking-by …

Retinex theory is developed mainly to decompose an image into the illumination and
reflectance components by analyzing local image derivatives. In this theory, larger …