NSFNet: Neural Scattering Field Network for 3D Imaging in ISAC Systems via Multi-View CSI Fusion
IEEE Transactions on Wireless Communications · 2026 · 25 · 14703-14718
DOI: 10.1109/twc.2026.3678616 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Wireless Communications, 2026. Verfasst von Jiapeng Li und 7 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben. Gefördert von: China Telecom Research Institute Project, National Natural Science Foundation of China, Beijing Municipal Natural Science Foundation.
Abstract (Originalsprache)
Integrated sensing and communication (ISAC) has emerged as a pivotal technology for next-generation wireless networks, enabling simultaneous high-speed communication and precise environmental awareness. This paper presents a novel ISAC imaging method, which leverages sparse multi-view channel state information (CSI) from existing communication infrastructure to reconstruct scattering fields, thereby achieving high-fidelity 3D imaging and environment reconstruction without the need for dedicated sensing hardware. A Neural Scattering Field Network (NSFNet) is designed to accomplish this task. The framework consists of two key components: 1) EdgeFusionNet, which extracts robust geometric features from sparse multi-view CSI using a multi-scale 3D CNN with edge-guided attention, and 2) MLP-based decoder that explicitly regresses view-dependent scattering coefficients, thereby addressing both the limited-view sampling challenge and the physical view-dependency of scattering. A self-supervised training strategy combining reconstruction loss and total variation regularization ensures accurate and smooth reconstructions. Experimental results demonstrate that NSFNet significantly outperforms compressed sensing and ablation deep learning baselines in complex scenarios, achieving superior performance in terms of F1-score (>0.83) and Chamfer Distance (
Förderung
- China Telecom Research Institute Project
- National Natural Science Foundation of China
- Beijing Municipal Natural Science Foundation
Zitieren
APA
Li, J., Qian, B., Zhang, Q., Wu, D., Ma, D., Huang, S., Zhang, J., & Feng, Z. (2026). NSFNet: Neural Scattering Field Network for 3D Imaging in ISAC Systems via Multi-View CSI Fusion. IEEE Transactions on Wireless Communications, 25, 14703-14718. https://doi.org/10.1109/twc.2026.3678616
Vancouver
Li J, Qian B, Zhang Q, Wu D, Ma D, Huang S, et al. NSFNet: Neural Scattering Field Network for 3D Imaging in ISAC Systems via Multi-View CSI Fusion. IEEE Transactions on Wireless Communications. 2026;25:14703-14718. doi:10.1109/twc.2026.3678616
BibTeX
@article{Li2026,
author = {Li, Jiapeng and Qian, Bing and Zhang, Qixun and Wu, Di and Ma, Dingyou and Huang, Sai and Zhang, Jianming and Feng, Zhiyong},
title = {NSFNet: Neural Scattering Field Network for 3D Imaging in ISAC Systems via Multi-View CSI Fusion},
journal = {IEEE Transactions on Wireless Communications},
year = {2026},
volume = {25},
pages = {14703--14718},
doi = {10.1109/twc.2026.3678616}
}
EUVIMED