Resolution-robust Large Mask In painting with Fourier Convolutions

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

We introduce and derive the Fourier -enhanced 3D electrostatic field solver of the gyrokinetic full -f PIC code PICLS. The solver makes use of a Fourier representation in one periodic direction of the domain to make the solving of the system easily paralle ...

We prove a sharp quantitative version of the Faber–Krahn inequality for the short-time Fourier transform (STFT). To do so, we consider a deficit which measures by how much the STFT of a function fails to be optimally concentrated on an arbitrary set of pos ...

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

The Schottky monitors of the Large Hadron Collider (LHC) can be used for non-invasive beam diagnostics to estimate various bunch characteristics, such as tune, chromaticity, bunch profile or synchrotron frequency distribution. However, collective effects, ...

Recent advancements in deep learning have revolutionized 3D computer vision, enabling the extraction of intricate 3D information from 2D images and video sequences. This thesis explores the application of deep learning in three crucial challenges of 3D com ...

Viewers of 360-degree videos are provided with both visual modality to characterize their surrounding views and audio modality to indicate the sound direction. Though both modalities are important for saliency prediction, little work has been done by joint ...

Modern power distribution systems are experiencing a large-scale integration of Converter-Interfaced Distributed Energy Resources (CIDERs). Their presence complicates the analysis and mitigation of harmonics, whose creation and propagation may be amplified ...

Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...

Traditionally, mass spectrometry (MS) output is the ion abundance plotted versus the ionic mass-to-charge ratio m/z. While employing only commercially available equipment, Charge Determination Analysis (CHARDA) adds a third dimension to MS, estimating for ...

The present work proposes a framework for nonlinear model order reduction based on a Graph Convolutional Autoencoder (GCA-ROM). In the reduced order modeling (ROM) context, one is interested in obtaining real -time and many-query evaluations of parametric ...

Current transformer-based skeletal action recognition models tend to focus on a limited set of joints and low-level motion patterns to predict action classes. This results in significant performance degradation under small skeleton perturbations or changin ...

Monitoring forests, in particular their response to climate and land use change, requires studying long time scales. While efficient deep learning methods have been developed to process short time series of satellite imagery, leveraging long time series of ...

The upcoming Square Kilometre Array Observatory will produce images of neutral hydrogen distribution during the epoch of reionization by observing the corresponding 21-cm signal. However, the 21-cm signal will be subject to instrumental limitations such as ...

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

The azimuthal anisotropy of gamma(1S) mesons in high-multiplicity proton-lead collisions is studied using data collected by the CMS experiment at a nucleon-nucleon center-of-mass energy of 8.16 TeV. The gamma(1S) mesons are reconstructed using their dimuon ...

In inverse problems, the task is to reconstruct an unknown signal from its possibly noise-corrupted measurements. Penalized-likelihood-based estimation and Bayesian estimation are two powerful statistical paradigms for the resolution of such problems. They ...

Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate scaled ResNet in the limit of infinitely deep and wide neural networks, of wh ...

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

In this thesis we explore the applications of projective geometry, a mathematical theory of the relation between 3D scenes and their 2D images, in modern learning-based computer vision systems. This is an interesting research question which contradicts the ...

Machine learning (ML) enables artificial intelligent (AI) agents to learn autonomously from data obtained from their environment to perform tasks. Modern ML systems have proven to be extremely effective, reaching or even exceeding human intelligence. Altho ...

Resolution-robust Large Mask In painting with Fourier Convolutions

Chat with Graph Search

Verification of the Fourier-enhanced 3D finite element Poisson solver of the gyrokinetic full-f code PICLS

Stability of the Faber-Krahn inequality for the short-time Fourier transform

Aggregating Spatial and Photometric Context for Photometric Stereo

Impact of beam-coupling impedance on the Schottky spectrum of bunched beam

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

SVGC-AVA: 360-Degree Video Saliency Prediction With Spherical Vector-Based Graph Convolution and Audio-Visual Attention

Unified Harmonic Power-Flow and Stability Analysis of Power Grids with Converter-Interfaced Distributed Energy Resources

Robust machine learning for neuroscientific inference

Adding Color to Mass Spectra of Biopolymers: Charge Determination Analysis (CHARDA) Assigns Charge State to Every Ion Peak

A graph convolutional autoencoder approach to model order reduction for parametrized PDEs

MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning

Multi-temporal forest monitoring in the Swiss Alps with knowledge-guided deep learning

Deep learning approach for identification of H II regions during reionization in 21-cm observations - II. Foreground contamination

Random matrix methods for high-dimensional machine learning models

Study of azimuthal anisotropy of γ(1S) mesons in pPb collisions at √SNN=8.16 TeV

Statistical Inference for Inverse Problems: From Sparsity-Based Methods to Neural Networks

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Incorporating Projective Geometry into Deep Learning

Few-shot Learning for Efficient and Effective Machine Learning Model Adaptation