DEEP LEARNING-BASED TEXTURE SYNTHESIS FOR SCULPTURAL REALISM
DOI:
https://doi.org/10.29121/shodhkosh.v6.i1s.2025.6631Keywords:
Deep Learning, Texture Synthesis, Sculptural Realism, Geometry-Aware Generation, UV Mapping, Generative Adversarial Networks, Differentiable Rendering, Multi-Scale Feature Learning, Perceptual LossAbstract [English]
In this paper, a multi-scale deep learning model that takes into account geometry to produce high-fidelity texture is proposed to condition on digital sculptures. The use of traditional 2D texture generation methods on complex 3D surfaces can be characterized by the presence of seam artifacts, distortions and disappearance of microstructural details, which makes them inappropriate in sculptural realism. The model is optimized on a multi-objective loss comprising of adversarial, perceptual and style components and patch-level and geometry-aware components and refined using differentiable rendering to match real lighting behaviour. It has been shown by experimental results of significantly better early results compared to classical techniques, StyleGAN-based baselines and diffusion based generators, lower perceptual error (LPIPS), seam discontinuity (SCI, PBD) and multi-view consistency. Human perceptual research supports that the suggested approach prevails in almost 70% of the pair-wise tests with references to greater material authenticity and geometric consistency. The results illustrate the usefulness of viewing texture synthesis as a 2D-3D joint learning task and define the introduced system as a potential source of digital sculpting, heritage modeling, virtual production, and high-end assets all of which require material realist.
References
Bellini, R., Kleiman, Y., and Cohen-Or, D. (2016). Time-Varying Weathering in Texture Space. ACM Transactions on Graphics (Proceedings of SIGGRAPH), 35(4), 1–11. https://doi.org/10.1145/2897824.2925966 DOI: https://doi.org/10.1145/2897824.2925891
Benaim, S., Mokady, R., Bermano, A., and Wolf, L. (2021). Structural Analogy from a Single Image Pair. Computer Graphics Forum, 40, 249–265. https://doi.org/10.1111/cgf.14256 DOI: https://doi.org/10.1111/cgf.14186
Cao, T., Kreis, K., Fidler, S., Sharp, N., and Yin, K. (2023). TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Models. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) (1–10). IEEE. DOI: https://doi.org/10.1109/ICCV51070.2023.00385
Chan, E. R., Lin, C. Z., Chan, M. A., Nagano, K., Pan, B., De Mello, S., Gallo, O., Guibas, L., Tremblay, J., Khamis, S., Karras, T., and Wetzstein, G. (2022). Efficient Geometry-Aware 3D Generative Adversarial Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (1–12). IEEE. DOI: https://doi.org/10.1109/CVPR52688.2022.01565
Chen, X., Jiang, T., Song, J., Yang, J., Black, M., Geiger, A., and Hilliges, O. (2022). gDNA: Towards Generative Detailed Neural Avatars. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (1–10). IEEE. DOI: https://doi.org/10.1109/CVPR52688.2022.01978
Chu, R. J., Richard, N., Chatoux, H., Fernandez-Maloigne, C., and Hardeberg, J. Y. (2021). Hyperspectral Texture Metrology Based on Joint Probability of Spectral and Spatial distribution. IEEE Transactions on Image Processing, 30, 4341–4356. https://doi.org/10.1109/TIP.2021.3084341 DOI: https://doi.org/10.1109/TIP.2021.3071557
Frühstück, A., Alhashim, I., and Wonka, P. (2019). TileGAN: Synthesis of large-scale non-homogeneous textures. ACM Transactions on Graphics (Proceedings of SIGGRAPH), 38(4), 1–11. https://doi.org/10.1145/3306346.3323020 DOI: https://doi.org/10.1145/3306346.3322993
Guerri, M. F., Distante, C., Spagnolo, P., Bougourzi, F., and Taleb-Ahmed, A. (2024). Deep Learning Techniques for Hyperspectral Image Analysis in Agriculture: A Review. ISPRS Open Journal of Photogrammetry and Remote Sensing, 12, Article 100062. https://doi.org/10.1016/j.ophoto.2024.100062 DOI: https://doi.org/10.1016/j.ophoto.2024.100062
Liu, L., Chen, B., Chen, H., Zou, Z., and Shi, Z. (2023). Diverse Hyperspectral Remote Sensing Image Synthesis with Diffusion Models. IEEE Transactions on Geoscience and Remote Sensing, 61, Article 5532616. https://doi.org/10.1109/TGRS.2023.5532616 DOI: https://doi.org/10.1109/TGRS.2023.3335975
Rajaei, A., Abiri, E., and Helfroush, M. S. (2024). Self-Supervised Spectral Super-Resolution for a Fast Hyperspectral and Multispectral Image Fusion. Scientific Reports, 14(1), 29820. https://doi.org/10.1038/s41598-024-29820 DOI: https://doi.org/10.1038/s41598-024-81031-8
Shabeer, S. M., Keerthi, K. L., Aditya, D. P., Priyanka, K., and Abhinay, L. (2025). Stylometric author identification via CNN-BiLSTM Architecture on Syntactic text Patterns. International Journal of Advanced Computer Engineering and Communication Technology (IJACECT), 14(1), 1–8. DOI: https://doi.org/10.65521/ijacect.v14i1.165
Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. A. (2017). Inception-v4, Inception-ResNet, and the Impact of Residual Connections on Learning. In Proceedings of the AAAI Conference on Artificial Intelligence. AAAI. DOI: https://doi.org/10.1609/aaai.v31i1.11231
Vaidya, C., Chopade, S., Khobragade, P., Bhure, K., and Parate, A. (2025). Development of a Face Recognition-Based Attendance System. In Proceedings of the 12th International Conference on Emerging Trends in Engineering and Technology – Signal and Information Processing (ICETET-SIP) (1–6). IEEE. https://doi.org/10.1109/ICETETSIP64213.2025.11156883 DOI: https://doi.org/10.1109/ICETETSIP64213.2025.11156883
Wang, P., Li, Y., and Vasconcelos, N. (2021). Rethinking and Improving the Robustness of Image Style Transfer. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (124–133). IEEE. DOI: https://doi.org/10.1109/CVPR46437.2021.00019
Wang, Z.-M., Li, M.-H., and Xia, G.-S. (2021). Conditional Generative Convnets for Exemplar-Based Texture Synthesis. IEEE Transactions on Image Processing, 30, 2461–2475. https://doi.org/10.1109/TIP.2021.3062475 DOI: https://doi.org/10.1109/TIP.2021.3052075
Yu, Y., Pan, E., MA, Y., Mei, X., Chen, Q., and Ma, J. (2024). UnmixDiff: Unmixing-Based Diffusion Model for Hyperspectral Image Synthesis. IEEE Transactions on Geoscience and Remote Sensing, 62, Article 5524018. https://doi.org/10.1109/TGRS.2024.5524018 DOI: https://doi.org/10.1109/TGRS.2024.3425517
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Dr. Shyamsing Thakur, Om Prakash, Dr. Kumud Saxena, Abhishek Singla, Dr. Sumalatha Potteti, Sonali Prashant Bhoite
This work is licensed under a Creative Commons Attribution 4.0 International License.
With the licence CC-BY, authors retain the copyright, allowing anyone to download, reuse, re-print, modify, distribute, and/or copy their contribution. The work must be properly attributed to its author.
It is not necessary to ask for further permission from the author or journal board.
This journal provides immediate open access to its content on the principle that making research freely available to the public supports a greater global exchange of knowledge.
