Learned 3D depth estimation and object detection via an integrated metasystem with wide field of view
Optics Express · 24.08.2026 · 34 (17) · 32534
DOI: 10.1364/oe.605731 ↗Kurz gefasst
Fachartikel in der Zeitschrift Optics Express, online erschienen am 19.08.2026. Verfasst von Zetao Yin und 9 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Beijing Municipal Natural Science Foundation, Beijing Outstanding Young Scientist Program.
Abstract (Originalsprache)
Object detection and 3D depth estimation have been widely adopted in autonomous driving, intelligent surveillance, augmented reality, and industrial automation, providing core support for scene perception, object-level interaction, and spatial understanding. Metasurfaces have recently risen to prominence in optical research, providing unique functionalities for imaging and 3D vision, while keeping device dimensions small. However, these meta-based 3D imaging methods mainly rely on binocular or multi-view vision, leading to an incompressible baseline dimension, especially working in the long distance. Here, we introduce an optimized metalens design and monocular depth estimation network for object detection and 3D depth recovery. By using the inverse-design metalens of wide field of view integrated with a commercial near-infrared sensor, we experimentally demonstrate the snapshot acquisition, high depth resolution, and accurate object detection ability. Additionally, we showcase the robustness of our approach by applying it to people and car detection in autonomous driving, highlighting its potential for deployment in embodied AI and industrial monitoring.
Förderung
- National Natural Science Foundation of China
- Beijing Municipal Natural Science Foundation
- Beijing Outstanding Young Scientist Program
- Science and Technology Commission of Beijing Municipal Education Commission
Zitieren
APA
Yin, Z., Jing, X., Ding, Y., Pan, S., Xue, J., Sun, C., Liu, Z., Wu, Z., Zhang, Z., & You, R. (2026). Learned 3D depth estimation and object detection via an integrated metasystem with wide field of view. Optics Express, 34(17), 32534. https://doi.org/10.1364/oe.605731
Vancouver
Yin Z, Jing X, Ding Y, Pan S, Xue J, Sun C, et al. Learned 3D depth estimation and object detection via an integrated metasystem with wide field of view. Optics Express. 2026;34(17):32534. doi:10.1364/oe.605731
BibTeX
@article{Yin2026,
author = {Yin, Zetao and Jing, Xiaoli and Ding, Yan and Pan, Sheng and Xue, Jidong and Sun, Chi and Liu, Zhaoxin and Wu, Zijue and Zhang, Zhongshan and You, Rui},
title = {Learned 3D depth estimation and object detection via an integrated metasystem with wide field of view},
journal = {Optics Express},
year = {2026},
volume = {34},
number = {17},
pages = {32534},
doi = {10.1364/oe.605731}
}
EUVIMED