Cover story: Wang YYD, Wang H, Gu M. High performance “non-local ” generic face reconstruction model using the lightweight Speckle-Transformer (SpT) UNet. Opto-Electron Adv 6, 220049 (2023).

Significant progress has been made in computational imaging (CI), in which deep convolutional neural networks (CNNs) have demonstrated that image reconstructions ranging from non-invasive medical imaging through the tissue

to autonomous navigation of vehicles in foggy conditions can be reconstructed. However, due to the limited “local” kernel size of the convolutional operator, the feature extraction ability of CNNs is limited especially for spatially dense patterns, such as the generic face images. In this article, a “non-local” model, termed the Speckle-Transformer (SpT) UNet, is implemented for highly accurate, energy-efficient parallel processing of the image reconstructions by Professor Min Gu’s group. It is worth noting that the SpT UNet is a lightweight network that is at least less than one order of parameters compared with other state-of-art “non-local” networks, such as ViT, and SWIN Transformer in vision. For the biomedical imaging, we believe that the network can be further implemented in complex tissue imaging to boost the image contrast and depth of range. For optical artificial intelligence, as the paralleling processing model, the SpT UNet can be further implemented as an all-optical neural network with surpassing feature extraction, light speed and passive processing abilities.