We inspect the ability to reproduce spectral (color) composition in random field-based texture models, test when it can neglect spectral correlation, and simplify these random models without visibly depreciating their visual quality. These probabilistic models present essential two or three-dimensiona...

In this study, we proposed a method for automatically generating high-quality CLIP(Contrastive Language Image Pre-training) training data to improve the performance of text-based image retrieval using CLIP. In general, two types of image-text pair data are used in CLIP training: correct pair...

We examine the influence of alcohol consumption on presence in Virtual Reality (VR) with both subjective and ob jective data. To measure the level of presence in VR we propose a method using four self-developed indicators, two subjective (Flow, Subjective Behaviour) and two objecti...

In this paper, we present a method for segmenting 3D discrete objects into discrete plane segments. This segmentation is the first step in obtaining a polyhedrization of a discrete object with the reversibility property. This constraint requires that the discretization result for polyhe...

The Industrial Metaverse offers new opportunities in various industrial sectors, such as product development, collaboration, sales and marketing. It relies on rendering 3D scenes of industrial plants, factories, and machines that are viewed by multiple human observers in various industrial applic...