Journal of Smart Energy Systems and Sustainable Technologies

Articles

Vol. 2 (2026)

Intelligent Evolution of Global Illumination Models and Their Applications in Virtual Power Scenarios

DOI:
https://doi.org/10.31875/2978-6436.2026.02.03
Submitted
July 27, 2026
Published
2026-07-27

Abstract

Illumination models are fundamental techniques in computer graphics for simulating realistic lighting effects and are widely applied in virtual reality, game development, and cinematic visual effects. With the continuous advancement of hardware capabilities and rendering algorithms, illumination models have become increasingly important in both real-time and offline rendering pipelines. This paper presents a comprehensive review of recent advances in illumination modeling and systematically analyzes representative studies in this field. Particular attention is given to neural-network-based light baking, dynamic global illumination, environment light mapping, neural rendering with Transformer architectures, illumination decomposition and editing, low-light image enhancement, real-time global illumination for VR/AR environments, as well as emerging high-order illumination representations and performance optimization strategies. Furthermore, this paper provides an in-depth discussion of intelligent illumination reconstruction for virtual power scenarios. Specifically, we introduce a semantic–pixel coupled probabilistic multi-cue illumination estimation model (SPC-PMC) designed for power operation simulation systems, together with its corresponding three-dimensional visualization framework. Through comparative analysis of these techniques, this study examines their underlying principles, characteristics, advantages, and limitations. Combined with illustrative figures and mathematical formulations, the paper highlights recent progress in improving rendering quality and computational efficiency, while also outlining future research directions in intelligent illumination modeling.

References

  1. Y. Gao, Y. Wang, N. Yang, Q. Wang, B. Javadi, Q. Ai, and J. Zhu, "Multi-timescale distributed control for multi-energy virtual power plant clusters via cloud-edge collaboration," Appl. Energy, vol. 414, Art. no. 127835, Jul. 2026. https://doi.org/10.1016/j.apenergy.2026.127835
  2. Y. Gao, X. Hu, T. Lü, Q. Ai, and X. He, "Digital twin control strategy for multi-energy virtual power plant considering vehicle-grid interaction and dynamic carbon trading," Power Syst. Technol., vol. 50, no. 2, pp. 683-698, Feb. 2026.
  3. S. López Flórez, G. Hernández González, J. Prieto, and F. de la Prieta, "Hybrid physics-LSTM framework for wind power prediction and control in virtual microgrid simulations," IEEE Access, vol. 13, pp. 122175-122186, Jul. 2025. https://doi.org/10.1109/ACCESS.2025.3586798
  4. J-F. Lalonde, A. A. Efros, and S. G. Narasimhan, "Estimating Natural Illumination from a Single Outdoor Image," Proc. IEEE Int. Conf. Comput. Vis., pp. 183-190, Sep. 2009. https://doi.org/10.1109/ICCV.2009.5459163
  5. A. Singh, U. Demirbaga, G. S. Aujla, A. Jindal, H. Sun, and J. Jiang, "Scalable and reliable data framework for sensor-enabled virtual power plant digital twin," IEEE J. Sel. Areas Sensors, vol. 2, pp. 108-120, 2025. https://doi.org/10.1109/JSAS.2025.3540956
  6. R. R. Rodriguez-Pardo, D. Dolonius, U. Assarsson, and E. Sintorn, "Spherical Gaussian Light-field Textures for Fast Precomputed Global Illumination," Comput. Graph. Forum, vol. 39, no. 2, pp. 133-146, 2020. https://doi.org/10.1111/cgf.13918
  7. Diolatzis, J. Philip, and G. Drettakis, "Active Exploration for Neural Global Illumination of Variable Scenes," ACM Trans. Graph., vol. 41, no. 5, Art. no. 171, 2022. https://doi.org/10.1145/3522735
  8. J. Guo, Z. Zong, Y. Song, X. Fu, C. Tao, Y. Guo, and L. Yan, "Efficient Light Probes for Real-time Global Illumination," ACM Trans. Graph., vol. 41, no. 4, Art. no. 202, 2022. https://doi.org/10.1145/3550454.3555452
  9. S. Rodriguez, T. Leimkuhler, S. Prakash, C. Wyman, P. Shirley, and G. Drettakis, "Glossy Probe Reprojection for Interactive Global Illumination," ACM Trans. Graph., vol. 39, no. 6, Art. no. 237, 2020. https://doi.org/10.1145/3414685.3417823
  10. N. Bus, N. H. Mustafa, and V. Biri, "Global illumination using well-separated pair decomposition," Comput. Graph. Forum, vol. 34, no. 8, pp. 88-103, 2015. https://doi.org/10.1111/cgf.12610
  11. K. Doi, Y. Morimoto, and R. Tsuruno, "Global Illumination-Aware Stylised Shading," Comput. Graph. Forum, vol. 40, no. 7, Art. no. 14397, 2021. https://doi.org/10.1111/cgf.14397
  12. Z. Majercik, T. Müller, A. Keller, D. Nowrouzezahrai, and M. McGuire, "Dynamic Diffuse Global Illumination Resampling," Comput. Graph. Forum, vol. 41, no. 1, pp. 158-171, 2022. https://doi.org/10.1111/cgf.14427
  13. N. Patakin, D. Senushkin, A. Vorontsova, and A. Konushin, "Neural global illumination for inverse rendering," in Proc. IEEE Int. Conf. Image Process. (ICIP), 2023. https://doi.org/10.1109/ICIP49359.2023.10222145
  14. D. Gao, H. Mu, and K. Xu, "Neural Global Illumination: Interactive Indirect Illumination Prediction Under Dynamic Area Lights," IEEE Trans. Vis. Comput. Graph., vol. 29, no. 12, 2023. https://doi.org/10.1109/TVCG.2022.3209963
  15. C. Zeng, Y. Dong, P. Peers, H. Wu, and X. Tong, "RenderFormer: Transformer-based neural rendering of triangle meshes with global illumination," in Proc. SIGGRAPH Conf. Papers, 2025, Art. no. 11. https://doi.org/10.1145/3721238.3730595
  16. S. Hadadan, G. Lin, J. Novák, F. Rousselle, and M. Zwicker, "Inverse global illumination using a neural radiometric prior," in Proc. SIGGRAPH Conf. Papers, 2023, Art. no. 11. https://doi.org/10.1145/3588432.3591553
  17. S. Mo, C. Zheng, Z. Lin, D. Xi, Q. Ye, R. Wang, H. Bao, and Y. Huo, "Dual-band feature fusion for neural global illumination with multi-frequency reflections," in Proc. SIGGRAPH Conf. Papers, 2025, Art. no. 11. https://doi.org/10.1145/3721238.3730733
  18. D. Hoiem, A. A. Efros, and M. Hebert, "Recovering Surface Layout from an Image," Int. J. Comput. Vis., vol. 75, no. 1, pp. 151-172, 2007. https://doi.org/10.1007/s11263-006-0031-y
  19. A. Meka, M. Shafiei, M. Zollhöfer, C. Richardt, and C. Theobalt, "Real-time Global Illumination Decomposition of Videos," ACM Trans. Graph., vol. 40, no. 3, Art. no. 22, 2021. https://doi.org/10.1145/3374753
  20. C. Rodriguez-Pardo, J. Fabre, E. Garces, and J. Lopez-Moreno, "NEnv: Neural Environment Maps for Global Illumination," Comput. Graph. Forum, vol. 42, no. 4, 2023. https://doi.org/10.1111/cgf.14883
  21. Y. Fang, W. Zhu, and Q. Zhu, "UGNet: Underexposed images enhancement network based on global illumination estimation," in Proc. IEEE Int. Conf. Vis. Commun. Image Process. (VCIP), 2020. https://doi.org/10.1109/VCIP49819.2020.9301810
  22. Z. Majercik, T. Müller, A. Keller, D. Nowrouzezahrai, and M. McGuire, "Dynamic diffuse global illumination resampling," in Proc. SIGGRAPH Talks, 2021, Art. no. 2. https://doi.org/10.1145/3450623.3464635
  23. N. Max, S. Saito, K. Watanabe, and M. Nakajima, "Rendering grass blowing in the wind with global illumination," Tsinghua Sci. Technol., vol. 15, no. 2, pp. 133-137, 2010. https://doi.org/10.1016/S1007-0214(10)70042-0
  24. W. Lü, J. Lu, X. Liu, and E. Wu, "A fast method for real-time computation of approximated global illumination," in Proc. 6th Int. Conf. Comput. Graph., Imaging Vis., 2009, pp. 62-68. https://doi.org/10.1109/CGIV.2009.24
  25. J. Noor, A. Mahmud, M. A. Rahman, A. Sifar, F. Y. Mostafa, L. Tasnova, and S. Chellappan, "SAwareSSGI: Surrounding-aware screen-space global illumination using generative adversarial networks," IEEE Access, vol. 12, pp. 139946-139961, 2024. https://doi.org/10.1109/ACCESS.2024.3467102
  26. Z. Shao, K. Zhang, D. Zhao, T. Wang, and T. Lu, "LLFA: Fusing global illumination and local priors for low-light face image enhancement with adaptor," in Proc. IEEE Int. Conf. Acoust., Speech Signal Process. (ICASSP), 2025. https://doi.org/10.1109/ICASSP49660.2025.10890118
  27. C. Wyman, S. Parker, P. Shirley, and C. Hansen, "Interactive display of isosurfaces with global illumination," IEEE Trans. Vis. Comput. Graph., vol. 12, no. 2, pp. 186-196, 2006. https://doi.org/10.1109/TVCG.2006.33
  28. J. Hilliard, A. Hilton, and J.-Y. Guillemaut, "HDR environment map estimation with latent diffusion models," arXiv:2507.21261, Jul. 2025.
  29. R. Liang, K. He, Z. Gojcic, I. Gilitschenski, S. Fidler, N. Vijaykumar, and Z. Wang, "LuxDiT: Lighting estimation with video diffusion transformer," Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), San Diego, CA, USA, Dec. 2025.
  30. C. Bolduc, J. Philip, L. Ma, M. He, P. Debevec, and J.-F. Lalonde, "Lighting in motion: Spatiotemporal HDR lighting estimation," Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2026.
  31. X. Zhao, P. P. Srinivasan, D. Verbin, K. Park, R. Martin-Brualla, and P. Henzler, "IllumiNeRF: 3D relighting without inverse rendering," Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), Vancouver, Canada, pp. 42593-42617, Dec. 2024. https://doi.org/10.52202/079017-1349
  32. Y. Wang, S. Song, L. Zhao, H. Xia, Z. Yuan, and Y. Zhang, "CGLight: An effective indoor illumination estimation method based on improved ConvMixer and GauGAN," Comput. Graph., vol. 125, Art. no. 104122, Dec. 2024. https://doi.org/10.1016/j.cag.2024.104122
  33. A. R. Anonymous et al., "Enhancing XR training with interactive AI-powered virtual instructors," IEEE MultiMedia, early access, 2025.
  34. X. Zhao, S. Zheng, L. Wang, Y. Wu, J. Zhao, and Y. Guo, "AA-COMT: An AI-driven AR system for communication operation and maintenance training," Proc. Int. Conf. Intell. Power Syst. (ICIPS), Yichang, China, pp. 963-967, Dec. 2024. https://doi.org/10.1109/ICIPS64173.2024.10900096
  35. Y.-Z. Lin, K. Petal, A. H. Alhamadah, S. Ghimire, M. W. Redondo, D. R. Vidal Corona, J. Pacheco, S. Salehi, and P. Satam, "Personalized education with generative AI and digital twins: VR, RAG, and zero-shot sentiment analysis for Industry 4.0 workforce development," arXiv:2502.14080, Feb. 2025.
  36. S. Yoo, S. Reza, H. Tarashiyoun, A. Ajikumar, and M. Moghaddam, "AI-integrated AR as an intelligent companion for industrial workers: A systematic review," IEEE Access, vol. 12, pp. 191808-191827, 2024. https://doi.org/10.1109/ACCESS.2024.3516536
  37. S. Yoo, C. Harteveld, N. Wilson, K. Jona, and M. Moghaddam, "Multimodal assessment of expertise in AR-guided psychomotor tasks," IEEE Trans. Syst., Man, Cybern.: Syst., vol. 55, no. 11, pp. 8126-8141, Nov. 2025. https://doi.org/10.1109/TSMC.2025.3604693
  38. V. Phadke, C. Harteveld, K. Jona, and M. Moghaddam, "First things first: Effects of sequential AR/VR exposure on skill acquisition in industrial training," Adv. Eng. Inform., vol. 71, Art. no. 104328, 2026. https://doi.org/10.1016/j.aei.2026.104328
  39. K. Witkowski, "Integrating VR, AR and AI into corporate employee training: A study of mixed methods towards personalized learning design," Management, vol. 2026, no. 1, pp. 70-95, Apr. 2026. https://www.management-poland.com/Integrating-VR-AR-and-AI-into-corporate-employee-training-A-study-of-mixed-methods,218508,0,2.html https://doi.org/10.58691/man/218508
  40. A. Alhakamy and M. Tuceryan, "CubeMap360: Interactive global illumination for augmented reality in dynamic environment," in Proc. IEEE Int. Symp. Mixed Augment. Reality (ISMAR), 2019. https://doi.org/10.1109/SoutheastCon42311.2019.9020588
  41. Y. Zhao, C. Ma, H. Huang, and T. Guo, "LitAR: Visually coherent lighting for mobile augmented reality," Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. (IMWUT), vol. 6, no. 3, Art. no. 153, Sep. 2022. https://doi.org/10.1145/3550291
  42. J. A. D. Gardner, E. Kashin, B. Egger, and W. A. P. Smith, "The sky's the limit: Relightable outdoor scenes via a sky-pixel constrained illumination prior and outside-in visibility," Proc. Eur. Conf. Comput. Vis. (ECCV), ser. LNCS, vol. 15112, Milan, Italy, pp. 126-143, Oct. 2024. https://doi.org/10.1007/978-3-031-72949-2_8
  43. A. Cosin Ayerbe, P. Poulin, and G. Patow, "Dynamic Voxel-Based Global Illumination," Comput. Graph. Forum, vol. 43, no. 1, 2024. https://doi.org/10.1111/cgf.15262
  44. J. Villegas and E. Ramírez, "Deferred voxel shading for real-time global illumination," in Proc. IEEE Pacific Graph. Conf., 2016. https://doi.org/10.1109/CLEI.2016.7833375
  45. F. Desrichard, D. Vanderhaeghe, and M. Paulin, "Global illumination shadow layers," Comput. Graph. Forum, vol. 38, no. 4, pp. 184-191, 2019. https://doi.org/10.1111/cgf.13781
  46. B. Wang, L. Wang, and N. Holzschuch, "Fast global illumination with discrete stochastic microfacets using a filterable model," Comput. Graph. Forum, vol. 37, no. 7, pp. 56-64, 2018. https://doi.org/10.1111/cgf.13547
  47. G. Laurent, C. Delalandre, G. De La Rivière, and T. Boubekeur, "Forward light cuts: A scalable approach to real-time global illumination," Comput. Graph. Forum, vol. 35, no. 4, pp. 80-88, 2016. https://doi.org/10.1111/cgf.12951
  48. B. Wang, X. Meng, and T. Boubekeur, "Wavelet point-based global illumination," Comput. Graph. Forum, vol. 34, no. 4, pp. 144-153, 2015. https://doi.org/10.1111/cgf.12686
  49. H. Dammertz, A. Keller, and H. P. A. Lensch, "Progressive point-light-based global illumination," Comput. Graph. Forum, vol. 29, no. 8, pp. 2504-2515, 2010. https://doi.org/10.1111/j.1467-8659.2010.01786.x
  50. P. Bauszat, M. Eisemann, S. John, and M. Magnor, "Sample-based manifold filtering for interactive global illumination and depth of field," Comput. Graph. Forum, vol. 34, no. 1, pp. 265-276, 2014. https://doi.org/10.1111/cgf.12511
  51. A. Gruson, M. Ribardière, and R. Cozot, "Eye-centered color adaptation in global illumination," Comput. Graph. Forum, vol. 32, no. 7, pp. 112-120, 2013. https://doi.org/10.1111/cgf.12218
  52. J. Kontkanen, E. Tabellion, and R. S. Overbeck, "Coherent out-of-core point-based global illumination," Comput. Graph. Forum, vol. 30, no. 4, pp. 1354-1360, 2011. https://doi.org/10.1111/j.1467-8659.2011.01995.x
  53. W. Tatzgern, B. Mayr, B. Kerbl, and M. Steinberger, "Stochastic substitute trees for real-time global illumination," in Proc. Symp. Interact. 3D Graph. Games, 2020, Art. no. 9. https://doi.org/10.1145/3384382.3384521
  54. J. Zhu, Z. Wu, Q. Zhang, C. Liao, and Z. Huang, "WishGI: Lightweight static global illumination baking via spherical harmonics fitting," ACM Trans. Graph., vol. 44, no. 4, Art. no. 72, 2025. https://doi.org/10.1145/3730935
  55. C. Luksch, M. Wimmer, and M. Schwärzler, "Incrementally baked global illumination," in Proc. Symp. Interact. 3D Graph. Games, 2019, Art. no. 2. https://doi.org/10.1145/3306131.3317015
  56. D. Nowrouzezahrai and J. Snyder, "Fast global illumination on dynamic height fields," Comput. Graph. Forum, vol. 28, no. 4, pp. 1132-1139, 2009. https://doi.org/10.1111/j.1467-8659.2009.01490.x
  57. R. Perez, R. Seals, and J. Michalsky, "All-Weather Model for Sky Luminance Distribution," Solar Energy, vol. 50, no. 3, pp. 235-245, 1993. https://doi.org/10.1016/0038-092X(93)90017-I
  58. M. Cavus, J. Jiang, A. Allahham, A. G. Rameshrao, E. Scullion, B. D. Malamud, H. Sun, and W. P. Ng, "Digital twins for hazard-resilient power grids: A systematic review and roadmap," Renew. Sustain. Energy Rev., vol. 235, Art. no. 116947, Mar. 2026. https://doi.org/10.1016/j.rser.2026.116947
  59. N. E. M. Barreto and A. R. Aoki, "Cyber-physical power system digital twins—A study on the state of the art," Energies, vol. 18, no. 22, Art. no. 5960, Nov. 2025. https://doi.org/10.3390/en18225960
  60. R. Liang, Z. Gojcic, H. Ling, J. Munkberg, J. Hasselgren, C.-H. Lin, J. Gao, A. Keller, N. Vijaykumar, S. Fidler, and Z. Wang, "Diffusion renderer: Neural inverse and forward rendering with video diffusion models," Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 26069-26080, Jun. 2025. https://openaccess.thecvf.com/content/CVPR2025/html/Liang_Diffusion_Renderer_Neural_Inverse_and_Forward_Rendering_with_Video_Diffusion_CVPR_2025_paper.html https://doi.org/10.1109/CVPR52734.2025.02428