Related papers: Deep-learning-driven end-to-end metalens imaging

Active metasurfaces, whose optical properties can be modulated post-fabrication, have emerged as an intensively explored field in recent years. The efforts to date, however, still face major performance limitations in tuning range, optical…

In the rapidly evolving field of optical engineering, precise alignment of multi-lens imaging systems is critical yet challenging, as even minor misalignments can significantly degrade performance. Traditional alignment methods rely on…

Metasurfaces have become a promising means for manipulating optical wavefronts in flat and high-performance optical devices. Conventional metasurface device design relies on trial-and-error methods to obtain target electromagnetic (EM)…

As the realm of spectral imaging applications extends its reach into the domains of mobile technology and augmented reality, the demands for compact yet high-fidelity systems become increasingly pronounced. Conventional methodologies,…

Recently, with the significant developments in deep learning techniques, solving underdetermined inverse problems has become one of the major concerns in the medical imaging domain. Typical examples include undersampled magnetic resonance…

Purpose: This study presents a variable resolution (VR) sampling and deep learning reconstruction approach for multi-spectral MRI near metal implants, aiming to reduce scan times while maintaining image quality. Background: The rising use…

The ongoing effort to implement compact and cheap optical systems is the main driving force for the recent flourishing research in the field of optical metalenses. Metalenses are a type of metasurface, used for focusing and imaging…

Recent image degradation estimation methods have enabled single-image super-resolution (SR) approaches to better upsample real-world images. Among these methods, explicit kernel estimation approaches have demonstrated unprecedented…

Volumetric imaging by fluorescence microscopy is often limited by anisotropic spatial resolution from inferior axial resolution compared to the lateral resolution. To address this problem, here we present a deep-learning-enabled…

Deep learning techniques have emerged as a promising approach to highly accelerated MRI. However, recent reconstruction challenges have shown several drawbacks in current deep learning approaches, including the loss of fine image details…

Multifocal lens, which focus incident light at multiple foci, are widely used in imaging systems and optical communications. However, for the traditional design strategy, it combines several lenses that have different focal points into a…

Metasurfaces have shown promising potentials in shaping optical wavefronts while remaining compact compared to bulky geometric optics devices. Design of meta-atoms, the fundamental building blocks of metasurfaces, relies on trial-and-error…

Deep learning has demonstrated superb efficacy in processing imaging data, yet its suitability in solving challenging inverse problems in scientific imaging has not been fully explored. Of immense interest is the determination of local…

Far-field characterization of small objects is severely constrained by the diffraction limit. Existing tools achieving sub-diffraction resolution often utilize point-by-point image reconstruction via scanning or labelling. Here, we present…

Most of the achievements in artificial intelligence so far were accomplished by supervised learning which requires numerous annotated training data and thus costs innumerable manpower for labeling. Unsupervised learning is one of the…

High-quality flat optical elements require efficient light deflection to large angles and over a wide wavelength spectrum. Although phase gradient metasurfaces achieve this by continuously adding phase shifts in the range of 0 to 2{\pi} to…

This chapter provides an overview of deep learning techniques for improving the spatial resolution of MRI, ranging from convolutional neural networks, generative adversarial networks, to more advanced models including transformers,…

Deep learning has revolutionized computer vision, yet a major gap persists between complex, data-hungry deep learning models and the practical demands of state-of-the-art scientific measurements. To fundamentally bridge this gap, we propose…

We propose a general topology optimization framework for metasurface inverse design that can automatically discover highly complex multi-layered meta-structures with increased functionalities. In particular, we present topology-optimized…

We present a deep learning framework based on a generative adversarial network (GAN) to perform super-resolution in coherent imaging systems. We demonstrate that this framework can enhance the resolution of both pixel size-limited and…