Article: Generation of virtual reality landscape scenes for digital urban architecture based on AI Journal: International Journal of Environment and Pollution (IJEP) 2026 Vol.76 No.8 pp.109 - 122 Abstract: This paper presents a new intelligent modelling method based on artificial intelligence and virtual reality technology to solve the problems of low efficiency, low accuracy and low resource utilisation in the traditional 3D modelling of digital city buildings. On the one hand, this technology can provide certain auxiliary effects on urban construction. On the other hand, it can complete safety drills for urban transportation, tourism promotion, and various major emergencies through simulation in VR urban architectural scenes. This paper mainly used relevant algorithms from machine learning (ML) in AI technology and computer vision (CV) technology to generate VR landscape scenes for digital urban architecture. Among them, ML has provided a data processing model for constructing VR landscape scenes of digital urban architecture, while CV technology has completed the preliminary modelling work of digital urban architecture by scanning architectural drawings or building entities. Experimental results demonstrate that the proposed method achieves a median geometric error of merely 0.034 metres in 3D reconstruction, with semantic segmentation accuracy reaching 96.3%. In complex scenarios, the modelling process completes in just 6.9 h while maintaining texture accuracy down to 1.8 pixels. The study reveals that integrating AI and VR technologies enables efficient and high-precision generation of virtual architectural landscapes for digital cities. This approach significantly enhances modelling automation and model realism, providing a practical technical solution for smart city development. Inderscience Publishers - linking academia, business and industry through research

Title: Generation of virtual reality landscape scenes for digital urban architecture based on AI

Authors: Dandan Dai; Bo Tu; Jingli Liu

Addresses: School of Art, East China Jiaotong University, Nanchang, 330013, Jiangxi, China ' School of Art, East China Jiaotong University, Nanchang, 330013, Jiangxi, China ' School of Art, East China Jiaotong University, Nanchang, 330013, Jiangxi, China

Abstract: This paper presents a new intelligent modelling method based on artificial intelligence and virtual reality technology to solve the problems of low efficiency, low accuracy and low resource utilisation in the traditional 3D modelling of digital city buildings. On the one hand, this technology can provide certain auxiliary effects on urban construction. On the other hand, it can complete safety drills for urban transportation, tourism promotion, and various major emergencies through simulation in VR urban architectural scenes. This paper mainly used relevant algorithms from machine learning (ML) in AI technology and computer vision (CV) technology to generate VR landscape scenes for digital urban architecture. Among them, ML has provided a data processing model for constructing VR landscape scenes of digital urban architecture, while CV technology has completed the preliminary modelling work of digital urban architecture by scanning architectural drawings or building entities. Experimental results demonstrate that the proposed method achieves a median geometric error of merely 0.034 metres in 3D reconstruction, with semantic segmentation accuracy reaching 96.3%. In complex scenarios, the modelling process completes in just 6.9 h while maintaining texture accuracy down to 1.8 pixels. The study reveals that integrating AI and VR technologies enables efficient and high-precision generation of virtual architectural landscapes for digital cities. This approach significantly enhances modelling automation and model realism, providing a practical technical solution for smart city development.

Keywords: virtual scene generation; digital city architecture; artificial intelligence; virtual reality; machine learning.

DOI: 10.1504/IJEP.2026.156122

International Journal of Environment and Pollution, 2026 Vol.76 No.8, pp.109 - 122

Received: 27 Oct 2025
Accepted: 06 Feb 2026
Published online: 04 Sep 2026 *

Title: Generation of virtual reality landscape scenes for digital urban architecture based on AI

Keep up-to-date