1 code implementation • ECCV 2020 • Federica Arrigoni, Luca Magri, Tomas Pajdla
Motion segmentation, i. e., the problem of clustering data in multiple images based on different 3D motions, is an important task for reconstructing and understanding dynamic scenes.
no code implementations • 18 Jan 2024 • Daniel Kelshaw, Luca Magri
The task is to uncover from the biased data the true state, which is the solution of the PDE.
1 code implementation • 9 Oct 2023 • Daniel Kelshaw, Luca Magri
Manifolds discovered by machine learning models provide a compact representation of the underlying data.
no code implementations • 6 Aug 2023 • Alberto Racca, Luca Magri
Extreme event are sudden large-amplitude changes in the state or observables of chaotic nonlinear systems, which characterize many scientific phenomena.
no code implementations • 19 Jun 2023 • Daniel Kelshaw, Luca Magri
We propose the physics-constrained convolutional neural network (PC-CNN) to infer the high-resolution solution from sparse observations of spatiotemporal and nonlinear partial differential equations.
no code implementations • 7 Jun 2023 • Daniel Kelshaw, Luca Magri
We show that the solutions inferred from the PC-CNN are physical, in contrast to the data corrupted by systematic errors that does not fulfil the governing equations.
no code implementations • 28 May 2023 • Tullio Traverso, Francesco Coletti, Luca Magri, Tassos G. Karayiannis, Omar K. Matar
The accurate prediction of the two-phase heat transfer coefficient (HTC) as a function of working fluids, channel geometries and process conditions is key to the optimal design and operation of compact heat exchangers.
no code implementations • 24 May 2023 • Daniel Kelshaw, Luca Magri
Geodesics on these manifolds define locally length-minimising curves and provide a notion of distance, which are key for reduced-order modelling, statistical inference, and interpolation.
no code implementations • 24 May 2023 • Elise Özalp, Georgios Margazoglou, Luca Magri
The forecasting and computation of the stability of chaotic systems from partial observations are tasks for which traditional equation-based methods may not be suitable.
1 code implementation • CVPR 2023 • Matteo Farina, Luca Magri, Willi Menapace, Elisa Ricci, Vladislav Golyanik, Federica Arrigoni
Geometric model fitting is a challenging but fundamental computer vision problem.
no code implementations • 3 Feb 2023 • Elise Özalp, Georgios Margazoglou, Luca Magri
We present the Physics-Informed Long Short-Term Memory (PI-LSTM) network to reconstruct and predict the evolution of unmeasured variables in a chaotic system.
no code implementations • 31 Jan 2023 • Nguyen Anh Khoa Doan, Alberto Racca, Luca Magri
The goal of this paper is to obtain an efficient and accurate reduced-order latent representation of a turbulent flow that exhibits extreme events.
no code implementations • ICCV 2023 • Andrea Porfiri Dal Cin, Giacomo Boracchi, Luca Magri
Traditional and deep Structure-from-Motion (SfM) methods typically operate under the assumption that the scene is rigid, i. e., the environment is static or consists of a single moving object.
no code implementations • 21 Nov 2022 • Alberto Racca, Nguyen Anh Khoa Doan, Luca Magri
The overarching objective of this paper is to propose a nonlinear decomposition of the turbulent state for a reduced-order representation of the dynamics.
no code implementations • 15 Nov 2022 • Luca Magri, Anh Khoa Doan
This decomposition finds the dominant directions in the curved latent space.
1 code implementation • 31 Oct 2022 • Daniel Kelshaw, Georgios Rigas, Luca Magri
In the absence of high-resolution samples, super-resolution of sparse observations on dynamical systems is a challenging problem with wide-reaching applications in experimental settings.
1 code implementation • 28 Oct 2022 • Daniel Kelshaw, Luca Magri
Measurements on dynamical systems, experimental or otherwise, are often subjected to inaccuracies capable of introducing corruption; removal of which is a problem of fundamental importance in the physical sciences.
no code implementations • 19 Aug 2022 • Zack Xuereb Conti, Ruchi Choudhary, Luca Magri
In this initial exploration, we evaluate the physics-based SDA framework on a demonstrative heat conduction scenario by varying the thermophysical properties of the source and target systems to demonstrate the transferability of mechanistic models from a physics-based domain to a data domain.
no code implementations • 25 Apr 2022 • Alberto Racca, Luca Magri
We show that echo state networks are able to predict extreme events well beyond the predictability time, i. e., up to more than five Lyapunov times.
1 code implementation • 20 Jan 2022 • Alberto Racca, Luca Magri
We asses whether the networks are able to extrapolate from the small imperfect datasets and predict the heavy-tail statistics that describe the events.
no code implementations • CVPR 2021 • Luca Magri, Filippo Leveni, Giacomo Boracchi
We address the problem of recovering multiple structures of different classes in a dataset contaminated by noise and outliers.
no code implementations • 17 Jun 2021 • Francisco Huhn, Luca Magri
Third, we find the set of flame parameters that minimize the time-averaged acoustic energy of chaotic oscillations, which are caused by the positive feedback with a heat source, such as a flame in gas turbines or rocket motors.
no code implementations • 15 Feb 2021 • Nguyen Anh Khoa Doan, Wolfgang Polifke, Luca Magri
We propose a physics-constrained machine learning method-based on reservoir computing- to time-accurately predict extreme events and long-term velocity statistics in a model of turbulent shear flow.
no code implementations • 9 Feb 2021 • Alberto Racca, Luca Magri
The proposed validation strategies, which are based on the dynamical systems properties of chaotic time series, are shown to outperform the state-of-the-art validation strategies.
no code implementations • ICCV 2021 • Andrea Porfiri Dal Cin, Luca Magri, Federica Arrigoni, Andrea Fusiello, Giacomo Boracchi
MultiSynch is a general solution that can cope with any linear group and we show to be profitably usable both on synthetic and real problems.
no code implementations • 28 Dec 2020 • Alberto Racca, Luca Magri
The network is showcased in the reconstruction of unmeasured (hidden) states of a chaotic system.
no code implementations • 20 Dec 2020 • Nguyen Anh Khoa Doan, Wolfgang Polifke, Luca Magri
We present an Auto-Encoded Reservoir-Computing (AE-RC) approach to learn the dynamics of a 2D turbulent flow.
no code implementations • 31 Oct 2020 • Nguyen Anh Khoa Doan, Wolfgang Polifke, Luca Magri
This approach is demonstrated on a chaotic Lorenz system and a truncation of the Charney-DeVore system.
1 code implementation • 20 Apr 2020 • Luca Magri, Nguyen Anh Khoa Doan
The coronavirus disease 2019 (COVID-19) has changed the world since the World Health Organization declared its outbreak on 30th January 2020, recognizing the outbreak as a pandemic on 11th March 2020.
Populations and Evolution
no code implementations • 9 Jan 2020 • Francisco Huhn, Luca Magri
We propose a physics-informed machine learning method to predict the time average of a chaotic attractor.
BIG-bench Machine Learning Physics-informed machine learning
no code implementations • 6 Jan 2020 • Nguyen Anh Khoa Doan, Wolfgang Polifke, Luca Magri
We extend the Physics-Informed Echo State Network (PI-ESN) framework to reconstruct the evolution of an unmeasured state (hidden state) in a chaotic system.
no code implementations • 23 Dec 2019 • Nguyen Anh Khoa Doan, Wolfgang Polifke, Luca Magri
We propose a physics-aware machine learning method to time-accurately predict extreme events in a turbulent flow.
no code implementations • CVPR 2019 • Luca Magri, Andrea Fusiello
This paper addresses the problem of multiple models fitting in the general context where the sought structures can be described by a mixture of heterogeneous parametric models drawn from different classes.
no code implementations • 9 Apr 2019 • Nguyen Anh Khoa Doan, Wolfgang Polifke, Luca Magri
We propose a physics-informed Echo State Network (ESN) to predict the evolution of chaotic systems.
no code implementations • 9 Apr 2019 • Tullio Traverso, Luca Magri
Reduced-order thermoacoustic models, which are nonlinear and time-delayed, can only qualitatively predict thermoacoustic oscillations.
no code implementations • 1 Mar 2019 • Hans Yu, Matthew P. Juniper, Luca Magri
Reduced-order models based on level-set methods are widely used tools to qualitatively capture and track the nonlinear dynamics of an interface.
no code implementations • CVPR 2016 • Luca Magri, Andrea Fusiello
This paper deals with the extraction of multiple models from noisy or outlier-contaminated data.
no code implementations • CVPR 2014 • Luca Magri, Andrea Fusiello
This paper presents an improvement of the J-linkage algorithm for fitting multiple instances of a model to noisy data corrupted by outliers.