Brick by brick, tile by tile.

Dolea, Alexandra

doi:10.2307/j.ctv2x8v66p.14

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These tiles have a rough, uneven surface, with irregular edges and divots that give them a distinctive, rustic look. The texture is intended to mimic the natural variations found in real brick, creating a warm, inviting ambiance in any space [32]. In figure 5, a set of Brick-styled ceramic tiles design is shown which has been used for training phase.…”

Section: Experimental Inputs: Marble and Brick Stylesmentioning

confidence: 99%

Devising Ceramic Tiles Texture featuring Semi-automatic Image Clustering and Generative Adversarial Networks

Abdullah

Chowdhury

Noor

et al. 2023

Preprint

View full text Add to dashboard Cite

Neural network-based generation has become a promising area of research with diverse applications in recent years, such as generating synthetic data, medical images, celebrity faces and so on. In this study, we try to investigate the potential of generative models in the field of ceramic tiles design. Specifically, we employ DCGAN and WGAN-GP to generate textures of ceramic tiles. Our dataset undergoes a semi-automated pre-processing stage, which has been crucial for achieving high-quality outputs. We analyse the performances and outputs of both the models. To examine the spatial quality of the produced outputs, employing statistical calculation and collecting survey reviews from professionals in the ceramic tile industry have been done to gather better insights. Our results demonstrate the potential of generative models for producing realistic ceramic tiles textures and suggest this work holds promise for improving the creativity and efficiency of ceramic tiles design process.

show abstract

Section: Experimental Inputs: Marble and Brick Stylesmentioning

confidence: 99%