Unsupervised learning enabled label-free single-pixel imaging for resilient information transmission through unknown dynamic scattering media
无监督学习实现了无标签单像素成像，以通过未知动态散射介质实现稳健的信息传输
教師なし学習により、未知の動的散乱媒質を介した頑健な情報伝送を可能にするラベルなし単一ピクセルイメージング
비지도 학습은 알려지지 않은 동적 산란 매질을 통한 내구성 있는 정보 전송을 위한 라벨 없는 단일 픽셀 이미징을 가능하게 했다.
El aprendizaje no supervisado permitió la imagen de un solo píxel sin etiquetas para la transmisión de información resistente a través de medios dinámicos de dispersión desconocidos
L'apprentissage non supervisé permet une imagerie à pixel unique sans étiquette pour une transmission d'information résiliente à travers des milieux de diffusion dynamique inconnus
Несмотря на обучение без учителя позволило осуществлять меток-свободное однопиксельное изображение для устойчивой передачи информации через неизвестные динамические рассеивающие среды
Fujie Li 李甫杰 ¹, Haoyu Zhang 张昊宇 ¹, Zhilan Lu 卢芝蓝 ¹, Li Yao 姚力 ¹, Yuan Wei 魏圆 ¹, Ziwei Li 李子薇 ¹, Feng Bao 鲍峰 ¹, Junwen Zhang 张俊文 ¹, Yingjun Zhou 周盈君 ¹, Nan Chi 迟楠 ¹ ²
¹ Key Laboratory for the Information Science of Electromagnetic Waves (MoE), Department of Communication Science and Engineering, Fudan University, Shanghai 200433, China
中国 上海 复旦大学电磁波信息科学教育部重点实验室
² Shanghai Engineering Research Center of Low-Earth-Orbit Satellite Communication and Applications, and Shanghai Collaborative Innovation Center of Low-Earth-Orbit Satellite Communication Technology, Shanghai 200433, China
中国 上海 上海低轨卫星通信与应用工程技术研究中心 上海市低轨卫星通信技术协同创新中心
Single-pixel imaging (SPI) is a prominent scattering media imaging technique that allows image transmission via one-dimensional detection under structured illumination, with applications spanning from long-range imaging to microscopy. Recent advancements leveraging deep learning (DL) have significantly improved SPI performance, especially at low compression ratios. However, most DL-based SPI methods proposed so far rely heavily on extensive labeled datasets for supervised training, which are often impractical in real-world scenarios.
Here, we propose an unsupervised learning-enabled label-free SPI method for resilient information transmission through unknown dynamic scattering media. Additionally, we introduce a physics-informed autoencoder framework to optimize encoding schemes, further enhancing image quality at low compression ratios. Simulation and experimental results demonstrate that high-efficiency data transmission with structural similarity exceeding 0.9 is achieved through challenging turbulent channels.
Moreover, experiments demonstrate that in a 5 m underwater dynamic turbulent channel, USAF target imaging quality surpasses traditional methods by over 13 dB. The compressive encoded transmission of 720×720 resolution video exceeding 30 seconds with great fidelity is also successfully demonstrated. These preliminary results suggest that our proposed method opens up a new paradigm for resilient information transmission through unknown dynamic scattering media and holds potential for broader applications within many other scattering media imaging technologies.
