Multimode-fiber Speckle Image Reconstruction Based on Multiscale Convolution and a Multidimensional Attention Mechanism

• Published in: Current optics and photonics 2024, 8(5), , pp.463-471
• Main Authors: Liu, Kai, Zhang, Leihong, Xu, Runchu, Zhang, Dawei, Yang, Haima, Sun, Quan
• Format: Article
• Language: English
• Subjects: Algorithms; Decoding; Encoders-Decoders; Feature extraction; Image enhancement; Image reconstruction; Image restoration; Image transmission; Neural networks; Pattern recognition; Speckle patterns; Waveforms; 물리학
• ISSN: 2508-7266; 2508-7274
• DOI: 10.3807/COPP.2024.8.5.463

Multimode fibers (MMFs) possess high information throughput and small core diameter, making them highly promising for applications such as endoscopy and communication. However, modal dispersion hinders the direct use of MMFs for image transmission. By training neural networks on time-series waveforms collected from MMFs it is possible to reconstruct images, transforming blurred speckle patterns into recognizable images. This paper proposes a fully convolutional neural-network model, MSMDFNet, for image restoration in MMFs. The network employs an encoder-decoder architecture, integrating multiscale convolutional modules in the decoding layers to enhance the receptive field for feature extraction. Additionally, attention mechanisms are incorporated from both spatial and channel dimensions, to improve the network's feature-perception capabilities. The algorithm demonstrates excellent performance on MNIST and Fashion-MNIST datasets collected through MMFs, showing significant improvements in various metrics such as SSIM.