Related papers: Generative Image Restoration and Super-Resolution …
The increasing use of generative ML foundation models for image restoration tasks such as super-resolution calls for robust and interpretable uncertainty quantification methods. We address this need by presenting a novel approach based on…
Scanning tunneling microscope (STM) is a powerful tool for studying the structural and electronic properties of materials at the atomic scale. The combination of low temperature and high magnetic field for STM and related spectroscopy…
The evaluation of synthetic micro-structure images is an emerging problem as machine learning and materials science research have evolved together. Typical state of the art methods in evaluating synthetic images from generative models have…
Deep neural networks have greatly promoted the performance of single image super-resolution (SISR). Conventional methods still resort to restoring the single high-resolution (HR) solution only based on the input of image modality. However,…
Scanning Transmission Electron Microscopy (STEM) has become the main stay for materials characterization on atomic level, with applications ranging from visualization of localized and extended defects to mapping order parameter fields. In…
Atomic resolution imaging is demonstrated using a hybrid scanning tunneling/near-field microwave microscope (microwave-STM). The microwave channels of the microscope correspond to the resonant frequency and quality factor of a coaxial…
Novel deep-learning (DL) architectures have reached a level where they can generate digital media, including photorealistic images, that are difficult to distinguish from real data. These technologies have already been used to generate…
The rapid advancement in self-supervised representation learning has highlighted its potential to leverage unlabeled data for learning rich visual representations. However, the existing techniques, particularly those employing different…
This paper proposes a new two-step procedure for sparse-view tomographic image reconstruction. It is called RISING, since it combines an early-stopped Rapid Iterative Solver with a subsequent Iteration Network-based Gaining step. So far,…
State-of-the-art methods for semantic segmentation of images involve computationally intensive neural network architectures. Most of these methods are not adaptable to high-resolution image segmentation due to memory and other computational…
Generative deep learning architectures can produce realistic, high-resolution fake imagery -- with potentially drastic societal implications. A key question in this context is: How easy is it to generate realistic imagery, in particular for…
The nature of the atomic defects on the hydrogen passivated Si (100) surface is analyzed using deep learning and scanning tunneling microscopy (STM). A robust deep learning framework capable of identifying atomic species, defects, in the…
With the effective application of deep learning in computer vision, breakthroughs have been made in the research of super-resolution images reconstruction. However, many researches have pointed out that the insufficiency of the neural…
Despite the increased brilliance of the new generation synchrotron sources, there is still a challenge with high-resolution scanning of very thick and absorbing samples, such as the whole mouse brain stained with heavy elements, and,…
High resolution Atomic Force Microscopy (AFM) and Scanning Tunnelling Microscopy (STM) imaging with functionalized tips is well established, but a detailed understanding of the imaging mechanism is still missing. We present a numerical…
Automating quality inspection with computer vision techniques is often a very data-demanding task. Specifically, supervised deep learning requires a large amount of annotated images for training. In practice, collecting and annotating such…
Scanning tunnelling microscopy (STM) with a functionalized tip apex reveals the geometric and electronic structure of a sample within the same experiment. However, the complex nature of the signal makes images difficult to interpret and has…
Accurate 3D reconstruction from unstructured image collections is a key requirement in applications such as robotics, mapping, and scene understanding. While global Structure from Motion (SfM) techniques rely on full image connectivity and…
Scanning transmission electron microscopy is a common tool used to study the atomic structure of materials. It is an inherently multimodal tool allowing for the simultaneous acquisition of multiple information channels. Despite its…
In text recognition, self-supervised pre-training emerges as a good solution to reduce dependence on expansive annotated real data. Previous studies primarily focus on local visual representation by leveraging mask image modeling or…