Breaking the Resolution Barrier in Microscopic Imaging: An Optics-Preserving Super-Resolution System Combining Motion Modulation and Deep Learning

With the rapid development of micro/nano technology, the requirements for high-resolution images have become increasingly stringent. However, conventional microscopic imaging suffers from information degradation and irreversible sub-pixel detail loss, which fundamentally limits image quality improvement. To address this issue, this study designs a super resolution reconstruction system based on precision motion modulation and proposes a generative adversarial network (GAN) reconstruction algorithm incorporating variable sequence fusion and attention mechanisms to achieve super-resolution imaging. The proposed system implements a novel computational microscopy framework employing multi-spatial-view sampling, where a sliding-window-inspired acquisition strategy enables the systematic recovery of sub-pixel-scale image information that would otherwise be lost in conventional imaging. Subsequently, the GAN-based algorithm reconstructs high-resolution images. Experimental results demonstrate that the system effectively extends the sub-pixel information of the original image without modifying the existing optical-physical system. It enhances the model's reconstruction capability in terms of texture details and sharpness, significantly improving the overall quality of microscopic reconstructed images, and highlights the advantage of the algorithm in measurement accuracy.