Image-free inference for 3D object classification via multi-view single-pixel detection
Optics Letters · 01.09.2026 · 51 (17) · 4769
DOI: 10.1364/ol.608794 ↗Kurz gefasst
Fachartikel in der Zeitschrift Optics Letters, online erschienen am 17.08.2026. Verfasst von Siyuan Wang und 6 weiteren Autor:innen. Die Arbeit nennt 23 Literaturangaben. Gefördert von: National Key Laboratory of Air-based Information Perception and Fusions and the Aeronautical Science Fund, National Natural Science Foundation of China, Shaanxi Science and Technology Department.
Abstract (Originalsprache)
Image-free classification enables direct target recognition from single-pixel measurements without image reconstruction during inference, offering high sensing efficiency and low computational cost. However, existing approaches mainly rely on single-view observations and therefore cannot fully exploit the intrinsic three-dimensional (3D) structural information of real-world objects. Here, we propose a multi-view single-pixel detection framework for image-free inference of 3D object classes. By leveraging optical reciprocity, synchronized detectors acquire complementary view-dependent responses under identical spatial modulation patterns, enabling efficient extraction and fusion of stereoscopic features. A hybrid optical-neural architecture is developed, in which convolution kernels learned offline are converted into binary modulation patterns. A multi-view aircraft dataset containing five categories of 3D targets was established using a synchronized three-detector single-pixel imaging system. Experiments on the dataset demonstrate that multi-view fusion consistently outperforms single-view baselines. Statistical evaluation over 25 independent training runs shows that the proposed framework achieves 99.97% ± 0.06% with seven patterns. This work provides an effective route toward high-speed image-free 3D object perception in resource-constrained sensing applications.
Förderung
- National Key Laboratory of Air-based Information Perception and Fusions and the Aeronautical Science Fund
- National Natural Science Foundation of China
- Shaanxi Science and Technology Department
Zitieren
APA
Wang, S., Liu, M., Xu, J., Li, S., Gao, H., Bai, J., & Pan, A. (2026). Image-free inference for 3D object classification via multi-view single-pixel detection. Optics Letters, 51(17), 4769. https://doi.org/10.1364/ol.608794
Vancouver
Wang S, Liu M, Xu J, Li S, Gao H, Bai J, et al. Image-free inference for 3D object classification via multi-view single-pixel detection. Optics Letters. 2026;51(17):4769. doi:10.1364/ol.608794
BibTeX
@article{Wang2026,
author = {Wang, Siyuan and Liu, Muyuan and Xu, Jinghao and Li, Shengyi and Gao, Huiqin and Bai, Jinzhou and Pan, An},
title = {Image-free inference for 3D object classification via multi-view single-pixel detection},
journal = {Optics Letters},
year = {2026},
volume = {51},
number = {17},
pages = {4769},
doi = {10.1364/ol.608794}
}
EUVIMED