no code implementations • 25 Sep 2024 • Tashi Namgyal, Alexander Hepburn, Raul Santos-Rodriguez, Valero Laparra, Jesus Malo

The subjective quality of natural signals can be approximated with objective perceptual metrics.

no code implementations • 25 Jul 2024 • Pablo Hernández-Cámara, Jorge Vila-Tomás, Paula Dauden-Oliver, Nuria Alabau-Bosque, Valero Laparra, Jesús Malo

Autonomous driving is a challenging scenario for image segmentation due to the presence of uncontrolled environmental conditions and the eventually catastrophic consequences of failures.

1 code implementation • 25 Jul 2024 • Nuria Alabau-Bosque, Paula Daudén-Oliver, Jorge Vila-Tomás, Valero Laparra, Jesús Malo

Usually, these models are evaluated according to their ability to correlate with human opinion in databases with a range of distortions that may appear in digital media.

no code implementations • 6 Dec 2023 • Tashi Namgyal, Alexander Hepburn, Raul Santos-Rodriguez, Valero Laparra, Jesus Malo

Perceptual metrics are traditionally used to evaluate the quality of natural signals, such as images and audio.

no code implementations • 19 May 2023 • Tashi Namgyal, Alexander Hepburn, Raul Santos-Rodriguez, Valero Laparra, Jesus Malo

In this study, we investigate the feasibility of utilizing state-of-the-art image perceptual metrics for evaluating audio signals by representing them as spectrograms.

no code implementations • 17 Mar 2023 • Alexander Hepburn, Valero Laparra, Raúl Santos-Rodriguez, Jesús Malo

Moreover, the direct evaluation of the hypothesis was limited by the inability of the classical image models to deliver accurate estimates of the probability.

no code implementations • 26 Feb 2023 • Pablo Hernández-Cámara, Jorge Vila-Tomás, Valero Laparra, Jesús Malo

In this work, we perform a thorough analysis of the perceptual properties of pre-trained nets (particularly their ability to predict image quality) by isolating different factors: the goal (the function), the data (learning environment), the architecture, and the readout: selected layer(s), fine-tuning of channel relevance, and use of statistical descriptors as opposed to plain readout of responses.

no code implementations • 8 Jun 2022 • Valero Laparra, Alexander Hepburn, J. Emmanuel Johnson, Jesús Malo

Here we present the \emph{Convolutional RBIG}: an extension that alleviates this issue by imposing that the rotation in RBIG is a convolution.

no code implementations • 12 Apr 2022 • José A. Padrón-Hidalgo, Valero Laparra, Gustau Camps-Valls

Identifying low probability events in data/images is a challenging problem given the high-dimensionality of the data, especially when no (or little) information about the anomaly is available a priori.

1 code implementation • 7 Apr 2022 • Daniel Heestermans Svendsen, Daniel Hernández-Lobato, Luca Martino, Valero Laparra, Alvaro Moreno, Gustau Camps-Valls

Radiative transfer models (RTMs) encode the energy transfer through the atmosphere, and are used to model and understand the Earth system, as well as to estimate the parameters that describe the status of the Earth from satellite observations by inverse modeling.

1 code implementation • 25 Mar 2022 • Pablo Hernández-Cámara, Valero Laparra, Jesús Malo

In addition to the results on the Cityscapes and Foggy Cityscapes datasets, we explain these advantages through visualization of the responses: the equalization induced by the divisive normalization leads to more invariant features to local changes in contrast and illumination.

no code implementations • ICLR 2022 • Alexander Hepburn, Valero Laparra, Raul Santos-Rodriguez, Johannes Ballé, Jesús Malo

Since machine learning relies on the statistics of training data as well, the above connection has interesting implications when using perceptual distances (which mimic the behavior of the human visual system) as a loss function.

no code implementations • 22 Dec 2020 • Fernando Mateo, Jordi Munoz-Mari, Valero Laparra, Jochem Verrelst, Gustau Camps-Valls

Gaussian Processes (GPs) has experienced tremendous success in geoscience in general and for bio-geophysical parameter retrieval in the last years.

1 code implementation • 9 Dec 2020 • Juan Emmanuel Johnson, Valero Laparra, Gustau Camps-Valls

Gaussian Processes (GPs) are a class of kernel methods that have shown to be very useful in geoscience applications.

no code implementations • 9 Dec 2020 • David Malmgren-Hansen, Valero Laparra, Allan Aasbjerg Nielsen, Gustau Camps-Valls

We compare Principal Component Analysis (PCA) and Minimum Noise Fraction (MNF) for dimensionality reduction, and study the compactness and information content of the extracted features.

no code implementations • 9 Dec 2020 • José A. Padrón-Hidalgo, Valero Laparra, Nathan Longbotham, Gustau Camps-Valls

Anomalous change detection (ACD) is an important problem in remote sensing image processing.

no code implementations • 9 Dec 2020 • Emiliano Díaz, Adrián Pérez-Suay, Valero Laparra, Gustau Camps-Valls

This paper introduces a novel statistical regression framework that allows the incorporation of consistency constraints.

no code implementations • 9 Dec 2020 • David Malmgren-Hansen, Allan Aasbjerg Nielsen, Valero Laparra, Gustau Camps- Valls

The Infrared Atmospheric Sounding Interferometer (IASI) on board the MetOp satellite series provides important measurements for Numerical Weather Prediction (NWP).

no code implementations • 7 Dec 2020 • Adrián Pérez-Suay, Julia Amorós-López, Luis Gómez-Chova, Valero Laparra, Jordi Muñoz-Marí, Gustau Camps-Valls

Dealing with land cover classification of the new image sources has also turned to be a complex problem requiring large amount of memory and processing time.

no code implementations • 7 Dec 2020 • Gustau Camps-Valls, Luca Martino, Daniel H. Svendsen, Manuel Campos-Taberner, Jordi Muñoz-Marí, Valero Laparra, David Luengo, Francisco Javier García-Haro

However, GPs are typically used for inverse modeling based on concurrent observations and in situ measurements only.

2 code implementations • 2 Dec 2020 • J. Emmanuel Johnson, Valero Laparra, Gustau Camps-Valls, Raul Santos-Rodríguez, Jesús Malo

Density destructors are differentiable and invertible transforms that map multivariate PDFs of arbitrary structure (low entropy) into non-structured PDFs (maximum entropy).

3 code implementations • 13 Oct 2020 • J. Emmanuel Johnson, Valero Laparra, Maria Piles, Gustau Camps-Valls

Information theory is an excellent framework for analyzing Earth system data because it allows us to characterize uncertainty and redundancy, and is universally interpretable.

4 code implementations • 8 Oct 2020 • Valero Laparra, J. Emmanuel Johnson, Gustau Camps-Valls, Raul Santos-Rodríguez, Jesus Malo

Information theory is an outstanding framework to measure uncertainty, dependence and relevance in data and systems.

2 code implementations • 29 Jul 2020 • J. Emmanuel Johnson, Valero Laparra, Adrián Pérez-Suay, Miguel D. Mahecha, Gustau Camps-Valls

We note that model function derivatives in kernel machines is proportional to the kernel function derivative.

1 code implementation • 10 Jun 2020 • Gonzalo Mateo-García, Valero Laparra, Dan López-Puigdollers, Luis Gómez-Chova

In addition, the training of the proposed adversarial domain adaptation model can be modified to improve the performance in a specific remote sensing application, such as cloud detection, by including a dedicated term in the cost function.

1 code implementation • 20 May 2020 • J. Emmanuel Johnson, Valero Laparra, Gustau Camps-Valls

In this letter, we demonstrate how one can account for input noise estimates using a GP model formulation which propagates the error terms using the derivative of the predictive mean function.

no code implementations • 28 Oct 2019 • Alexander Hepburn, Valero Laparra, Jesús Malo, Ryan McConville, Raul Santos-Rodriguez

Traditionally, the vision community has devised algorithms to estimate the distance between an original image and images that have been subject to perturbations.

no code implementations • 9 Aug 2019 • Alexander Hepburn, Valero Laparra, Ryan McConville, Raul Santos-Rodriguez

While an important part of the evaluation of the generated images usually involves visual inspection, the inclusion of human perception as a factor in the training process is often overlooked.

no code implementations • 16 Oct 2017 • Adrián Pérez-Suay, Valero Laparra, Gonzalo Mateo-García, Jordi Muñoz-Marí, Luis Gómez-Chova, Gustau Camps-Valls

It has been shown that not including sensitive features that bias fairness, such as gender or race, is not enough to mitigate the discrimination when other related features are included.

no code implementations • NeurIPS 2017 • Alexander Berardino, Johannes Ballé, Valero Laparra, Eero P. Simoncelli

We develop a method for comparing hierarchical image representations in terms of their ability to explain perceptual sensitivity in humans.

no code implementations • 23 Jan 2017 • Valero Laparra, Alex Berardino, Johannes Ballé, Eero P. Simoncelli

We develop a framework for rendering photographic images, taking into account display limitations, so as to optimize perceptual similarity between the rendered image and the original scene.

13 code implementations • 5 Nov 2016 • Johannes Ballé, Valero Laparra, Eero P. Simoncelli

We describe an image compression method, consisting of a nonlinear analysis transformation, a uniform quantizer, and a nonlinear synthesis transformation.

no code implementations • 18 Jul 2016 • Johannes Ballé, Valero Laparra, Eero P. Simoncelli

We introduce a general framework for end-to-end optimization of the rate--distortion performance of nonlinear transform codes assuming scalar quantization.

no code implementations • 2 Jun 2016 • Valero Laparra, Jesus Malo

The identified curvilinear features can be interpreted as a set of nonlinear sensors: the response of each sensor is the projection onto the corresponding feature.

no code implementations • 9 Mar 2016 • Emma Izquierdo-Verdiguier, Valero Laparra, Robert Jenssen, Luis Gómez-Chova, Gustau Camps-Valls

Results show that 1) OKECA returns projections with more expressive power than KECA, 2) the most successful rule for estimating the kernel parameter is based on maximum likelihood, and 3) OKECA is more robust to the selection of the length-scale parameter in kernel density estimation.

no code implementations • 31 Jan 2016 • Valero Laparra, Jesus Malo, Gustau Camps-Valls

DRR identifies the nonlinear features through multivariate regression to ensure the reduction in redundancy between he PCA coefficients, the reduction of the variance of the scores, and the reduction in the reconstruction error.

no code implementations • 31 Jan 2016 • Valero Laparra, Sandra Jiménez, Devis Tuia, Gustau Camps-Valls, Jesús Malo

Moreover, PPA shows a number of interesting analytical properties.

7 code implementations • IEEE Transactions on Neural Networks 2011 • Valero Laparra, Gustavo Camps-Valls, Jesús Malo

The practical performance of RBIG is successfully illustrated in a number of multidimensional problems such as image synthesis, classification, denoising, and multi-information estimation.

no code implementations • 31 Jan 2016 • Valero Laparra, Juan Gutiérrez, Gustavo Camps-Valls, Jesús Malo

In this paper, we propose an alternative non-explicit way to take into account the relations among natural image wavelet coefficients for denoising: we use support vector regression (SVR) in the wavelet domain to enforce these relations in the estimated signal.

no code implementations • 31 Jan 2016 • Valero Laparra, Sandra Jiménez, Gustavo Camps-Valls, Jesús Malo

Here we address the simultaneous statistical explanation of (i) the nonlinear behavior of achromatic and chromatic mechanisms in a fixed adaptation state, and (ii) the change of such behavior.

2 code implementations • 19 Nov 2015 • Johannes Ballé, Valero Laparra, Eero P. Simoncelli

The data are linearly transformed, and each component is then normalized by a pooled activity measure, computed by exponentiating a weighted sum of rectified and exponentiated components and a constant.

Cannot find the paper you are looking for? You can
Submit a new open access paper.

Contact us on:
hello@paperswithcode.com
.
Papers With Code is a free resource with all data licensed under CC-BY-SA.