Related papers: Generative Image Restoration and Super-Resolution …
Scanning Transmission Electron Microscopy (STEM) enables the observation of atomic arrangements at sub-angstrom resolution, allowing for atomically resolved analysis of the physical and chemical properties of materials. However, due to the…
We consider the problem of trustworthy image restoration, taking the form of a constrained optimization over the prior density. To this end, we develop generative models for the task of image super-resolution that respect the degradation…
Camera pipelines receive raw Bayer-format frames that need to be denoised, demosaiced, and often super-resolved. Multiple frames are captured to utilize natural hand tremors and enhance resolution. Multi-frame super-resolution is therefore…
We propose a new method for atomic-scale imaging of spatial current patterns in nanoscopic quantum networks by using scanning tunneling microscopy (STM). By measuring the current flowing from the STM tip into one of the leads attached to…
Large medical imaging data sets are becoming increasingly available, but ensuring sample quality without significant artefacts is challenging. Existing methods for identifying imperfections in medical imaging rely on data-intensive…
In machine learning based single image super-resolution, the degradation model is embedded in training data generation. However, most existing satellite image super-resolution methods use a simple down-sampling model with a fixed kernel to…
The amount of training data that is required to train a classifier scales with the dimensionality of the feature data. In hyperspectral remote sensing, feature data can potentially become very high dimensional. However, the amount of…
State-of-the-art (SOTA) Generative Models (GMs) can synthesize photo-realistic images that are hard for humans to distinguish from genuine photos. Identifying and understanding manipulated media are crucial to mitigate the social concerns…
Single atom/molecule manipulation with a scanning-tunneling-microscope (STM) tip is an innovative experimental technique of nanoscience. Using STM-tip as an engineering or analytical tool, artificial atomic-scale structures can be…
Data augmentation is crucial for pixel-wise annotation tasks like semantic segmentation, where labeling requires significant effort and intensive labor. Traditional methods, involving simple transformations such as rotations and flips,…
In this work, we develop a novel technique for reconstructing images from projection-based nano- and microtomography. Our contribution focuses on enhancing reconstruction quality, particularly for specimen composed of homogeneous material…
Scanning Transmission Electron Microscopy (STEM) offers high-resolution images that are used to quantify the nanoscale atomic structure and composition of materials and biological specimens. In many cases, however, the resolution is limited…
Generative artificial intelligence has transformed the generation of synthetic data, providing innovative solutions to challenges like data scarcity and privacy, which are particularly critical in fields such as medicine. However, the…
Methods based on convolutional neural network (CNN) have demonstrated tremendous improvements on single image super-resolution. However, the previous methods mainly restore images from one single area in the low resolution (LR) input, which…
Spiking neural networks (SNNs) offer a promising alternative to current artificial neural networks to enable low-power event-driven neuromorphic hardware. Spike-based neuromorphic applications require processing and extracting meaningful…
We introduce a novel control mode for Scanning Tunneling Microscopy (STM) that leverages di/dz feedback. By superimposing a high-frequency sinusoidal modulation on the control signal, we extract the amplitude of the resulting tunneling…
The identification and removal of systematic errors in object detectors can be a prerequisite for their deployment in safety-critical applications like automated driving and robotics. Such systematic errors can for instance occur under very…
Novel multimodal imaging methods are capable of generating extensive, super high resolution datasets for preclinical research. Yet, a massive lack of annotations prevents the broad use of deep learning to analyze such data. So far, existing…
Imaging through complex scattering media is severely limited by aberrations and scattering which obscure images and reduce resolution. Confocal and temporal gatings partly filter out multiple scattering but are severely degraded by…
We introduce a generative smoothness regularization on manifolds (SToRM) model for the recovery of dynamic image data from highly undersampled measurements. The model assumes that the images in the dataset are non-linear mappings of…