Related papers: Deep-learning-driven end-to-end metalens imaging
Metalenses, featuring ultra-compactness and CMOS compatibility, are limited by the compromise between the diameter, numerical aperture, and working waveband. To address this problem, we propose and numerically demonstrate a centimeter-scale…
Most of the classical denoising methods restore clear results by selecting and averaging pixels in the noisy input. Instead of relying on hand-crafted selecting and averaging strategies, we propose to explicitly learn this process with deep…
We present full-Maxwell topology-optimization design of a single-piece multlayer metalens, about 10 wavelengths~$\lambda$ in thickness, that simultaneously focuses over a $60^\circ$ angular range and a 23\% spectral bandwidth without…
In latest years, deep learning has gained a leading role in the pansharpening of multiresolution images. Given the lack of ground truth data, most deep learning-based methods carry out supervised training in a reduced-resolution domain.…
Given a degraded input image, image restoration aims to recover the missing high-quality image content. Numerous applications demand effective image restoration, e.g., computational photography, surveillance, autonomous vehicles, and remote…
The reconstruction of a high resolution image given a low resolution observation is an ill-posed inverse problem in imaging. Deep learning methods rely on training data to learn an end-to-end mapping from a low-resolution input to a…
The concept of metasurfaces was recently applied to the extreme ultraviolet (EUV) spectral regime, providing a new opportunity for transmissive focusing elements in a regime where materials are highly lossy. The realization of metalenses in…
We present a new latent model of natural images that can be learned on large-scale datasets. The learning process provides a latent embedding for every image in the training dataset, as well as a deep convolutional network that maps the…
In this paper, we introduce deep learning technology to tackle two traditional low-level image processing problems, companding and inverse halftoning. We make two main contributions. First, to the best knowledge of the authors, this is the…
In recent years, the majority of works on deep-learning-based image colorization have focused on how to make a good use of the enormous datasets currently available. What about when the data at disposal are scarce? The main objective of…
Metalenses, which exhibit superior light-modulating performance with sub-micrometer-scale thicknesses, are suitable alternatives to conventional bulky refractive lenses. However, fabrication limitations, such as a high cost, low throughput,…
In the field of fusing multi-spectral and panchromatic images (Pan-sharpening), the impressive effectiveness of deep neural networks has been recently employed to overcome the drawbacks of traditional linear models and boost the fusing…
Recently, an achromatic metasurface was successfully demonstrated to deflect light of multiple wavelengths in the same direction and it was further applied to the design of planar lenses without chromatic aberrations [Science, 347,…
Flexible control light field across multiple parameters is the cornerstone of versatile and miniaturized optical devices. Metasurfaces, comprising subwavelength scatterers, offer a potent platform for executing such precise manipulations.…
Image-text matching is a key multimodal task that aims to model the semantic association between images and text as a matching relationship. With the advent of the multimedia information age, image, and text data show explosive growth, and…
Deep learning methods have been successfully applied to various computer vision tasks. However, existing neural network architectures do not per se incorporate domain knowledge about the addressed problem, thus, understanding what the model…
Conventional metalenses control light by varying meta-atom geometry, a design strategy that inherently couples phase modulation to structural dimensions and exacerbates chromatic dispersion. Here, we break this paradigm by decoupling phase…
Optical systems with wide field-of-views (FOV) are crucial for many applications such as high performance imaging, optical projection, augmented/virtual reality, and miniaturized medical imaging tools. Typically, aberration-free imaging…
Ultrathin and flat optical lenses are essential for modern optical imaging, spectroscopy, and energy harvesting. Dielectric metasurfaces comprising nanoscale quasi-periodic resonator arrays are promising for such applications, as they can…
Image processing and edge detection are at the core of several newly emerging technologies, such as augmented reality, autonomous driving and more generally object recognition. Image processing is typically performed digitally using…