Development of Seamless PBR Textures for 3D Amigurumi Doll Objects with an AI-assisted Image Processing Approach

T. Rafli Abdillah; Muhammad Erfan Syah; Ledyana Fitriani; Iskandar Zulkarnaini

doi:10.61992/jiem.v7i1.152

T. Rafli Abdillah Almuslim University
Muhammad Erfan Syah Almuslim University
Ledyana Fitriani Almuslim University
Iskandar Zulkarnaini Almuslim University

DOI: https://doi.org/10.61992/jiem.v7i1.152

Keywords: PBR, seamless textures, AI, image processing, amigurumi, Photoshop, 3D textures.

Abstract

The demand for high-quality 3D assets in the animation and multimedia industry is increasing. One of the main challenges in developing 3D models is the availability of realistic and seamless PBR (Physically Based Rendering) textures, especially for fabric-based objects such as amigurumi dolls. This study aims to develop seamless PBR textures based on reference photos of amigurumi dolls using an AI-assisted image processing approach . The process begins with data collection in the form of amigurumi doll photos, which are then processed using generative AI technology to generate initial texture patterns. Next, Adobe Photoshop is used for refinement so that the textures meet seamless standards and PBR components such as diffuse/albedo, normal, and roughness maps. The results show that this approach can produce high-quality PBR textures efficiently compared to manual methods. These findings can be used as a reference in the production of textile-based 3D assets for animation, games, and interactive learning media.

References

Deng, W., Ke, W., Deng, Z., & Wang, X. (2024). Virtual design of woven fabrics based on parametric modeling and physically based rendering. Computer-Aided Design, 173, 103717. https://doi.org/https://doi.org/10.1016/j.cad.2024.103717
Foundation, B. (2025). Blender Manual: Working with PBR Textures. Blender Foundation.
Hu, A., Desai, N., Abu Alhaija, H., Kim, S. W., & Shugrina, M. (2024). Diffusion Texture Painting. Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers ’24, 1–12. https://doi.org/10.1145/3641519.3657458
Isola, P., Zhu, J.-Y., Zhou, T., & A., A. (2018). Image-to-Image Translation with Conditional Adversarial Networks. Computer Vision and Pattern Recognition, 3.
Karras, T., Laine, S., & Aila, T. (2019). A Style-Based Generator Architecture for Generative Adversarial Networks. Computer Science, 3.
Ma, K., & Chung, J. (2023). A Research on 3D Texture Production Using Artificial Intelligence Softwear. International Journal of Internet, Broadcasting and Communication, 15, 178–184. https://doi.org/10.7236/IJIBC.2023.15.4.178
Pharr, M., Jakob, W., & Humphreys, G. (2016). Physically Based Rendering: From Theory to Implementation (3rd ed.). Morgan Kaufmann Publishers Inc. https://infoscience.epfl.ch/handle/20.500.14299/128083
Sajjadi, M. S. M., Scholkopf, B., & Hirsch, M. (2017). EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis. Computer Science, 2.
Yan Zhu, J., Park, T., Isola, P., & Efros, A. A. (2020). Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks. Computer Science, 7.