Far-field super-resolution ghost imaging with a deep neural network constraint
具有深度神经网络约束的远场超分辨率鬼成像
深いニューラルネットワーク制約を伴う遠方場超解像ゴーストイメージング
심층 신경망 제약 조건이 있는 원거리 초해상도 고스트 이미징
Imágenes fantasma de superresolución de campo lejano con una restricción de red neuronal profunda
Imagerie fantôme de super-résolution en champ lointain avec une contrainte de réseau neuronal profond
Призрачное изображение в дальнем поле сверхвысокого разрешения с ограничением глубокой нейронной сети
Fei Wang ¹ ², Chenglong Wang 王成龙 ¹ ², Mingliang Chen 陈明亮 ¹ ², Wenlin Gong 龚文林 ¹ ², Yu Zhang ¹, Shensheng Han 韩申生 ¹ ² ³ ⁴, Guohai Situ 司徒国海 ¹ ² ³ ⁴
¹ Shanghai Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Shanghai 201800, China
中国 上海 中国科学院上海光学精密机械研究所
² Center of Materials Science and Optoelectronics Engineering, University of Chinese Academy of Sciences, Beijing 100049, China
中国 北京 中国科学院大学 材料科学与光电工程中心
³ Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024, China
中国 杭州 中国科学院大学杭州高等研究院
⁴ CAS Center for Excellence in Ultra-intense Laser Science, Shanghai 201800, China
中国科学院 超强激光科学卓越创新中心
Ghost imaging (GI) facilitates image acquisition under low-light conditions by single-pixel measurements and thus has great potential in applications in various fields ranging from biomedical imaging to remote sensing. However, GI usually requires a large amount of single-pixel samplings in order to reconstruct a high-resolution image, imposing a practical limit for its applications.
Here we propose a far-field super-resolution GI technique that incorporates the physical model for GI image formation into a deep neural network. The resulting hybrid neural network does not need to pre-train on any dataset, and allows the reconstruction of a far-field image with the resolution beyond the diffraction limit. Furthermore, the physical model imposes a constraint to the network output, making it effectively interpretable.
We experimentally demonstrate the proposed GI technique by imaging a flying drone, and show that it outperforms some other widespread GI techniques in terms of both spatial resolution and sampling ratio. We believe that this study provides a new framework for GI, and paves a way for its practical applications.
