Related papers: Self-supervised prior learning improves structured…
The information recoverable from galaxy spectra depends fundamentally on spectral resolution, yet assembling large samples at high resolution remains observationally expensive. We present a deep-learning framework for spectral…
We present a study that evaluates the impact of regularization on the achieved resolution in restorations from a novel three-dimensional (3D) Structured Illumination Microscopy (3D-SIM) system with desirable tunability properties. This…
Intensity correlation microscopy (ICM), which is prominently known through antibunching microscopy or super-resolution optical fluctuation imaging (SOFI), provides superresolution through a correlation analysis of antibunching of…
Self-supervised learning (SSL) with Vision Transformers (ViT) has shown immense potential in medical image analysis. However, the quadratic complexity ($\mathcal{O}(N^2)$) of standard self-attention poses a severe barrier for…
Super-resolution is generally referred to as the task of recovering fine details from coarse information. Motivated by applications such as single-molecule imaging, radar imaging, etc., we consider parameter estimation of complex…
Leveraging the multilayer realization of programmable metasurfaces, stacked intelligent metasurfaces (SIM) enable fine-grained wave-domain control. However, their wideband deployment is impeded by two structural factors: (i) a single,…
Image Phase Alignment Super-Sampling (ImPASS) is a computational imaging algorithm for converting a sequence of displaced low-resolution images into a single high-resolution image. The method consists of a unique combination of Phase…
Poor lighting conditions significantly impact image quality, posing substantial challenges for image editing and visualization. Many existing enhancement methods aim at proposing complex models while neglecting the intrinsic information…
Though structured illumination (SI) microscopy is a popular imaging technique conventionally associated with fluorescent super-resolution, recent works have suggested its applicability towards sub-diffraction coherent imaging with…
Background and objective: High-resolution radiographic images play a pivotal role in the early diagnosis and treatment of skeletal muscle-related diseases. It is promising to enhance image quality by introducing single-image…
Structured reconstruction is a non-trivial dense prediction problem, which extracts structural information (\eg, building corners and edges) from a raster image, then reconstructs it to a 2D planar graph accordingly. Compared with common…
Retinal implants aim to restore functional vision despite photoreceptor degeneration, yet are fundamentally constrained by low resolution electrode arrays and patient-specific perceptual distortions. Most deployed encoders rely on…
Real world image super-resolution (Real-ISR) often leverages the powerful generative priors of text-to-image diffusion models by regularizing the output to lie on their learned manifold. However, existing methods often overlook the…
Diffusion-based super-resolution (SR) models have recently garnered significant attention due to their potent restoration capabilities. But conventional diffusion models perform noise sampling from a single distribution, constraining their…
Hyperspectral imaging (HSI) enables detailed land cover classification, yet low spatial resolution and sparse annotations pose significant challenges. We present a label-efficient framework that leverages spatial features from a frozen…
In Super-resolution, a varying-illumination image stack is required. This enriched the dataset typically necessitates precise mechanical control and micron scale optical alignment and repeatability. Here, we introduce a novel methodology…
Confocal microscopy has long been a cornerstone technique for visualizing complex interactions and processes within cellular structures. However, achieving super-resolution imaging of multiple organelles and their interactions…
Infrared small object detection urgently requires semi-supervised paradigms due to the high cost of annotation. However, existing methods like SAM face significant challenges of domain gaps, inability of encoding physical priors, and…
While researches on model-based blind single image super-resolution (SISR) have achieved tremendous successes recently, most of them do not consider the image degradation sufficiently. Firstly, they always assume image noise obeys an…
Self-supervised representation learning methods often fail to learn subtle or complex features, which can be dominated by simpler patterns which are much easier to learn. This limitation is particularly problematic in applications to…