Related papers: Shape-Dependent, Deep-Learning-Assisted Metamateri…
Structured illumination microscopy (SIM) achieves superresolution in fluorescence imaging through patterned illumination and computational image reconstruction, yet current methods require bulky, costly modulation optics and high-precision…
In the recent past, significant research efforts have been put forth to fabricate low-cost noble metal-free substrates for surface-enhanced Raman spectroscopy (SERS) applications. Here we propose semiconducting TiO2 multi-leg nanotubes…
Conventional deep learning models deal with images one-by-one, requiring costly and time-consuming expert labeling in the field of medical imaging, and domain-specific restriction limits model generalizability. Visual in-context learning…
The solid immersion lens is a powerful optical tool that allows light entering material from air or vacuum to focus to a spot much smaller than the free-space wavelength. Conventionally, however, they rely on semispherical topographies and…
We present an ultrasensitive technique for probing transient optical changes in atomically thin molybdenum disulfide (MoS$_2$) layers integrated onto silicon nitride (Si$_3$N$_4$) ring resonators. The MoS$_2$ is illuminated by a femtosecond…
LiDAR sensors are often considered essential for autonomous driving, but high-resolution sensors remain expensive while affordable low-resolution sensors produce sparse point clouds that miss critical details. LiDAR super-resolution…
This letter presents a theoretical and experimental study on the viability of obtaining three dimensional super-resolution (i.e. resolution overcoming the diffraction limit for all directions in space) by means of metamaterial slab lenses.…
In the domain of scientific imaging, interpreting visual data often demands an intricate combination of human expertise and deep comprehension of the subject materials. This study presents a novel methodology to linguistically emulate and…
Fluorescence lifetime imaging microscopy (FLIM) is a powerful quantitative technique that provides metabolic and molecular contrast, offering strong translational potential for label-free, real-time diagnostics. However, its clinical…
Semiconductor-based surface-enhanced Raman spectroscopy (SERS) substrates, as a new frontier in the field of SERS, are hindered by their poor electromagnetic field confinement, and weak light-matter interaction. Metasurfaces, a class of 2D…
Recently, machine learning based single image super resolution (SR) approaches focus on jointly learning representations for high-resolution (HR) and low-resolution (LR) image patch pairs to improve the quality of the super-resolved images.…
Two-dimensional (2D) materials and heterostructures exhibit unique physical properties, necessitating efficient and accurate characterization methods. Leveraging advancements in artificial intelligence, we introduce a deep learning-based…
Most of the recent Deep Semantic Segmentation algorithms suffer from large generalization errors, even when powerful hierarchical representation models based on convolutional neural networks have been employed. This could be attributed to…
Hyperspectral imaging (HSI) captures spatial and spectral data, enabling analysis of features invisible to conventional systems. The technology is vital in fields such as weather monitoring, food quality control, counterfeit detection,…
In this work, we address the critical yet underexplored challenge of symmetric multimodal-to-multimodal (MM2MM) retrieval, where queries and contexts are interchangeable. Existing universal multimodal retrieval works struggle with this…
State-of-the-art deep learning models are often trained with a large amount of costly labeled training data. However, requiring exhaustive manual annotations may degrade the model's generalizability in the limited-label regime.…
Optical Fourier surfaces (OFSs), featuring sinusoidally profiled diffractive elements, manipulate light through patterned nanostructures and incident angle modulation. Compared to altering structural parameters, tuning elevation and azimuth…
Masked Image Modelling (MIM) has been shown to be an efficient self-supervised learning (SSL) pre-training paradigm when paired with transformer architectures and in the presence of a large amount of unlabelled natural images. The…
Grayscale lithography allows the creation of micrometer-scale features with spatially-controlled height in a process that is fully compatible with standard lithography. Here, solid immersion lenses are demonstrated in silicon carbide using…
Deep supervision, which involves extra supervisions to the intermediate features of a neural network, was widely used in image classification in the early deep learning era since it significantly reduces the training difficulty and eases…