AUTOMATION OF DIGITAL TEXTURE GENERATION USING GENERATIVE ARTIFICIAL INTELLIGENCE MODELS
DOI:
https://doi.org/10.32689/maup.it.2026.2.3Keywords:
generative artificial intelligence, texture generation, diffusion models, digital materials, three-dimensional modeling, computer graphics, physically based rendering, automation, machine learningAbstract
The study aims to substantiate an approach to automating digital texture generation with generative artificial intelligence models and to define a reproducible sequence of operations for producing materials suitable for three-dimensional modeling systems. The paper systematizes recent approaches based on diffusion models, material-oriented generative methods, and methods that synthesize textures directly in the surface or UV space of three-dimensional objects. A critical review of Point-UV Diffusion, MatFuse, DiffMat, DreamMat, Single Mesh Diffusion Models, and TEXGen is provided to identify their main advantages and limitations. An automated texture generation workflow is proposed. It includes defining material requirements, constructing a text or visual prompt, generating candidate results, evaluating their compliance with the requirements, preparing material maps, post-processing, and exporting the result to a three-dimensional environment. Two practical cases are described: an aged brick surface and a matte metal material. For each case, the input requirements, an example prompt, evaluation criteria, and the sequence of preparing the material for a 3D scene are specified. The study argues that generative artificial intelligence should be treated not as a complete replacement for a specialist, but as a tool for automating repetitive operations and rapidly producing design alternatives. The practical value of the study lies in a reproducible workflow that can be applied to game development, digital design, architectural visualization, and the training of information technology specialists.
References
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y. (2014). Generative Adversarial Nets. Advances in Neural Information Processing Systems. Vol. 27.
Ho, J., Jain, A., Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems. Vol. 33.
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B. (2022). High-Resolution Image Synthesis with Latent Diffusion Models. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. P. 10684–10695. DOI: 10.1109/CVPR52688.2022.01042.
Yu, X., Dai, P., Li, W., Ma, L., Liu, Z., Qi, X. (2023). Texture Generation on 3D Meshes with Point-UV Diffusion. Proceedings of the IEEE/CVF International Conference on Computer Vision. P. 4206–4216.
Vecchio, G., Sortino, R., Palazzo, S., Spampinato, C. (2024). MatFuse: Controllable Material Generation with Diffusion Models. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. P. 4429–4438. DOI: 10.1109/CVPR52733.2024.00424.
Zhang, Y., Liu, Y., Xie, Z., Yang, L., Liu, Z., Yang, M., Zhang, R., Kou, Q., Lin, C., Wang, W., Jin, X. (2024). DreamMat: High-quality PBR Material Generation with Geometry- and Light-aware Diffusion Models. ACM Transactions on Graphics. Vol. 43, No. 4. DOI: 10.1145/3658170.
Zhang, C., et al. (2024). DiffMat: Latent diffusion models for image-guided material generation. Visual Informatics. Vol. 8, No. 1. P. 6–14. DOI: 10.1016/j.visinf.2023.12.001.
Mitchel, T.W., Esteves, C., Makadia, A. (2024). Single Mesh Diffusion Models with Field Latents for Texture Generation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. P. 7953–7963. DOI: 10.1109/CVPR52733.2024.00760.
Yu, X., Yuan, Z., Guo, Y.-C., Liu, Y.-T., Liu, J., Li Y., Cao, Y.-P., Liang, D., Qi, X. (2024). TEXGen: A Generative Diffusion Model for Mesh Textures. ACM Transactions on Graphics. Vol. 43, No. 6, Article 213. DOI: 10.1145/3687909.
Huang, X., Wang, T., Liu, Z., Wang, Q. (2024). Material Anything: Generating Materials for Any 3D Object via Diffusion. arXiv preprint arXiv:2411.15138.
Xie, Z., Zhang, Y., Tang, X., Wu, Y., Chen, D., Li, G., Jin, X. (2024). StyleTex: Style Image-Guided Texture Generation for 3D Models. ACM Transactions on Graphics.
Richardson, E., et al. (2023). TEXTure: Text-Guided Texturing of 3D Shapes. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.
Chen, A., et al. (2023). Text2Tex: Text-driven Texture Synthesis of 3D Shapes. Proceedings of the IEEE/CVF International Conference on Computer Vision.
Adobe. Substance 3D Sampler: Text-to-texture and Image-to-texture generative workflows. Adobe Experience League. 2024–2026.
Blender Foundation. Blender Manual: Materials and Texture Painting. 2025.
Epic Games. Unreal Engine Documentation: Materials and Textures. 2025.
Unity Technologies. Unity Manual: Materials, Textures and Shaders. 2025.
