|
Title:
|
SP3F-GAN: SEAMLESS TEXTURE MAPS GENERATION BY ADVERSARIAL EXTENSION FOR FASHION |
|
Author(s):
|
Honghong He, Zhengwentai Sun, Jintu Fan and Pik Yin Mok |
|
ISBN:
|
978-989-8704-49-8 |
|
Editors:
|
Katherine Blashki, Yingcai Xiao, Piet Kommers and Pedro Isaías |
|
Year:
|
2023 |
|
Edition:
|
Single |
|
Keywords:
|
Generative Adversarial Network (GAN), Seamless Texture Synthesis, BRDFs |
|
Type:
|
Full |
|
First Page:
|
161 |
|
Last Page:
|
167 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
Creating seamless textures is essential for achieving realistic virtual objects and environments. This paper proposes a method for automatic seamless texture synthesis by designing a tiled latent space in the generator of an adversarial expansion network, resulting in a continuous texture output at the seam intersection area. In addition, considering the different properties of virtual environment rendering materials, the spatially varying BRDFs (albedo, normal, roughness and displacement map) are all designed in the proposed model to handle multi-layer texture representation. Qualitative and quantitative experiments on the describable textures dataset (DTD) show that the generated texture maps are not only seamlessly tiled but also exhibit superior visual quality in preserving details compared to previous deep texture synthesis methods. |
|
|
|
|
|
|
