Overview of automated 3d space construction methods from videos using artificial intelligence
JOURNAL OF SCIENCE AND DEVELOPMENT ECONOMICS · 13.06.2026 · (4) · 147-161
DOI: 10.64632/jsde.eng.4.2026.906 ↗Kurz gefasst
Fachartikel in der Zeitschrift JOURNAL OF SCIENCE AND DEVELOPMENT ECONOMICS, online erschienen am 13.06.2026. Verfasst von Phan Thi Xuan Trang und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This research focuses on studying, reviewing, and analyzing methods for automatically reconstructing 3D spatial structures from single-image video data (monocular video) through the integration of modern artificial intelligence models such as Deep Learning and 3D Gaussian Splatting. This solution overcomes the cost and time limitations of traditional photometric methods, providing real-time processing capabilities with superior photorealistic image quality. Simultaneously, the research applies a multi-dimensional evaluation system based on metrics such as PSNR, LPIPS, and FPS to optimize the balance between geometric accuracy and operational performance on common devices.
Zitieren
APA
Trang, P. T. X., Huy, D. M., Trinh, B. T. D., & Nam, T. T. (2026). Overview of automated 3d space construction methods from videos using artificial intelligence. JOURNAL OF SCIENCE AND DEVELOPMENT ECONOMICS, 147-161. https://doi.org/10.64632/jsde.eng.4.2026.906
Vancouver
Trang PTX, Huy DM, Trinh BTD, Nam TT. Overview of automated 3d space construction methods from videos using artificial intelligence. JOURNAL OF SCIENCE AND DEVELOPMENT ECONOMICS. 2026:147-161. doi:10.64632/jsde.eng.4.2026.906
BibTeX
@article{Trang2026,
author = {Trang, Phan Thi Xuan and Huy, Dang Manh and Trinh, Bui Thi Diem and Nam, Tran Thanh},
title = {Overview of automated 3d space construction methods from videos using artificial intelligence},
journal = {JOURNAL OF SCIENCE AND DEVELOPMENT ECONOMICS},
year = {2026},
number = {4},
pages = {147--161},
doi = {10.64632/jsde.eng.4.2026.906}
}
EUVIMED