Related papers: Separate Universe Super-Resolution Emulator
Magnetic resonance imaging (MRI) is a widely used medical imaging modality. However, due to the limitations in hardware, scan time, and throughput, it is often clinically challenging to obtain high-quality MR images. The super-resolution…
Super-resolution (SR) for image enhancement has great importance in medical image applications. Broadly speaking, there are two types of SR, one requires multiple low resolution (LR) images from different views of the same object to be…
Simulation is increasingly being used for generating large labelled datasets in many machine learning problems. Recent methods have focused on adjusting simulator parameters with the goal of maximising accuracy on a validation task, usually…
Generalizable neural surface reconstruction has become a compelling technique to reconstruct from few images without per-scene optimization, where dense 3D feature volume has proven effective as a global representation of scenes. However,…
In real-world single image super-resolution (SISR) task, the low-resolution image suffers more complicated degradations, not only downsampled by unknown kernels. However, existing SISR methods are generally studied with the synthetic…
Single image super-resolution traditionally assumes spatially-invariant degradation models, yet real-world imaging systems exhibit complex distance-dependent effects including atmospheric scattering, depth-of-field variations, and…
Scanning tunnelling microscopy (STM) enables atomic-resolution imaging and atom manipulation, but its utility is often limited by tip degradation and slow serial data acquisition. Fabrication adds another layer of complexity since the tip…
High-fidelity simulation of complex physical systems is exorbitantly expensive and inaccessible across spatiotemporal scales. Recently, there has been an increasing interest in leveraging deep learning to augment scientific data based on…
Modern-day display systems demand high-quality rendering. However, rendering at higher resolution requires a large number of data samples and is computationally expensive. Recent advances in deep learning-based image and video…
Realistic hyperspectral image (HSI) super-resolution (SR) techniques aim to generate a high-resolution (HR) HSI with higher spectral and spatial fidelity from its low-resolution (LR) counterpart. The generative adversarial network (GAN) has…
Accurate modeling of supernova (SN) feedback in galaxy formation simulations is complicated by energy conservation violations arising from the vector nature of momentum injection. We present a mechanical feedback scheme addressing two key…
Single Image Super Resolution (SISR) is a well-researched problem with broad commercial relevance. However, most of the SISR literature focuses on small-size images under 500px, whereas business needs can mandate the generation of very high…
We present the results of the first multi-scale N-Body+SPH simulations of merging galaxies containing central supermassive black holes (SMBHs) and having a spatial resolution of only a few parsecs. Strong gas inflows associated with…
Neutrino mass constraints are a primary focus of current and future large-scale structure (LSS) surveys. Non-linear LSS models rely heavily on cosmological simulations -- the impact of massive neutrinos should therefore be included in these…
To overcome inherent hardware limitations of hyperspectral imaging systems with respect to their spatial resolution, fusion-based hyperspectral image (HSI) super-resolution is attracting increasing attention. This technique aims to fuse a…
We propose a new method for generating equilibrium models of spherical systems of collisionless particles that are finite in extent, but whose central regions resemble dark matter halos from cosmological simulations. This method involves…
In this article we propose and numerically implement a mathematical model for the simulation of three-dimensional semiconductor devices characterized by an heterogeneous material structure. The model consists of a system of nonlinearly…
Existing deep architectures cannot operate on very large signals such as megapixel images due to computational and memory constraints. To tackle this limitation, we propose a fully differentiable end-to-end trainable model that samples and…
Deep learning-based single image super-resolution enables very fast and high-visual-quality reconstruction. Recently, an enhanced super-resolution based on generative adversarial network (ESRGAN) has achieved excellent performance in terms…
We propose a temporally coherent generative model addressing the super-resolution problem for fluid flows. Our work represents a first approach to synthesize four-dimensional physics fields with neural networks. Based on a conditional…