1.3k citations · 2.4k across the 52 of their papers we have counts for
23 papers · 1 filter
Human-AI Perceptual Alignment by Playing Hues and Cues
Nuria Alabau-Bosque, Jorge Vila-Tomás, Paula Daudén-Oliver +3
Evaluating the perceptual alignment between Contrastive Vision-Language Models (CVLMs) and humans is typically constrained by traditional benchmarks that overlook fine-grained sema…
Parameter-Efficient Architectural Modifications for Translation-Invariant CNNs
Nuria Alabau-Bosque, Jorge Vila-Tomas, Paula Dauden-Oliver +2
Convolutional Neural Networks (CNNs) are widely assumed to be translation-invariant, yet standard architectures exhibit a startling fragility: even a single-pixel shift can drastic…
Color Names in Vision-Language Models
Alexandra Gomez-Villa, Pablo Hernández-Cámara, Muhammad Atif Butt +3
Color serves as a fundamental dimension of human visual perception and a primary means of communicating about objects and scenes. As vision-language models (VLMs) become increasing…
Hues and Cues: Human vs. CLIP
Nuria Alabau-Bosque, Jorge Vila-Tomás, Paula Daudén-Oliver +4
Playing games is inherently human, and a lot of games are created to challenge different human characteristics. However, these tasks are often left out when evaluating the human-li…
From Images to Perception: Emergence of Perceptual Properties by Reconstructing Images
Pablo Hernández-Cámara, Jesus Malo, Valero Laparra
A number of scientists suggested that human visual perception may emerge from image statistics, shaping efficient neural representations in early vision. In this work, a bio-inspir…
Do Vision Transformers See Like Humans? Evaluating their Perceptual Alignment
Pablo Hernández-Cámara, Jose Manuel Jaén-Lorites, Jorge Vila-Tomás +2
Vision Transformers (ViTs) achieve remarkable performance in image recognition tasks, yet their alignment with human perception remains largely unexplored. This study systematicall…
Contrast Sensitivity in Multimodal Large Language Models: A Psychophysics-Inspired Evaluation
Pablo Hernández-Cámara, Alexandra Gomez-Villa, Jose Manuel Jaén-Lorites +3
Understanding how Multimodal Large Language Models (MLLMs) process low-level visual features is critical for evaluating their perceptual abilities and has not been systematically c…
On the dynamic evolution of CLIP texture-shape bias and its relationship to human alignment and model robustness
Pablo Hernández-Cámara, Jose Manuel Jaén-Lorites, Alexandra Gómez-Villa +3
Contrastive language-image models such as CLIP have demonstrated remarkable generalization capabilities. However, how their internal visual representations evolve during training a…
RAID-Database: human Responses to Affine Image Distortions
Paula Daudén-Oliver, David Agost-Beltran, Emilio Sansano-Sansano +3
Image quality databases are used to train models for predicting subjective human perception. However, most existing databases focus on distortions commonly found in digital media a…
Parametric PerceptNet: A bio-inspired deep-net trained for Image Quality Assessment
Jorge Vila-Tomás, Pablo Hernández-Cámara, Valero Laparra +1
Human vision models are at the core of image processing. For instance, classical approaches to the problem of image quality are based on models that include knowledge about human v…
Assessing invariance to affine transformations in image quality metrics
Nuria Alabau-Bosque, Paula Daudén-Oliver, Jorge Vila-Tomás +2
Subjective image quality metrics are usually evaluated according to the correlation with human opinion in databases with distortions that may appear in digital media. However, thes…
Image Segmentation via Divisive Normalization: dealing with environmental diversity
Pablo Hernández-Cámara, Jorge Vila-Tomás, Paula Dauden-Oliver +3
Autonomous driving is a challenging scenario for image segmentation due to the presence of uncontrolled environmental conditions and the eventually catastrophic consequences of fai…
Image Statistics Predict the Sensitivity of Perceptual Quality Metrics
Alexander Hepburn, Valero Laparra, Raúl Santos-Rodriguez +1
Previously, Barlow and Attneave hypothesised a link between biological vision and information maximisation. Following Shannon, information was defined using the probability of natu…
Analysis of Deep Image Quality Models
Pablo Hernández-Cámara, Jorge Vila-Tomás, Valero Laparra +1
Subjective image quality measures based on deep neural networks are very related to models of visual neuroscience. This connection benefits engineering but, more interestingly, the…
Orthonormal Convolutions for the Rotation Based Iterative Gaussianization
Valero Laparra, Alexander Hepburn, J. Emmanuel Johnson +1
In this paper we elaborate an extension of rotation-based iterative Gaussianization, RBIG, which makes image Gaussianization possible. Although RBIG has been successfully applied t…
Neural Networks with Divisive normalization for image segmentation with application in cityscapes dataset
Pablo Hernández-Cámara, Valero Laparra, Jesús Malo
One of the key problems in computer vision is adaptation: models are too rigid to follow the variability of the inputs. The canonical computation that explains adaptation in sensor…
On the relation between statistical learning and perceptual distances
Alexander Hepburn, Valero Laparra, Raul Santos-Rodriguez +2
It has been demonstrated many times that the behavior of the human visual system is connected to the statistics of natural images. Since machine learning relies on the statistics o…
Kernel Anomalous Change Detection for Remote Sensing Imagery
José A. Padrón-Hidalgo, Valero Laparra, Nathan Longbotham +1
Anomalous change detection (ACD) is an important problem in remote sensing image processing. Detecting not only pervasive but also anomalous or extreme changes has many application…
Enforcing Perceptual Consistency on Generative Adversarial Networks by Using the Normalised Laplacian Pyramid Distance
Alexander Hepburn, Valero Laparra, Ryan McConville +1
In recent years there has been a growing interest in image generation through deep learning. While an important part of the evaluation of the generated images usually involves visu…
Eigen-Distortions of Hierarchical Representations
Alexander Berardino, Johannes Ballé, Valero Laparra +1
We develop a method for comparing hierarchical image representations in terms of their ability to explain perceptual sensitivity in humans. Specifically, we utilize Fisher informat…
Perceptually Optimized Image Rendering
Valero Laparra, Alex Berardino, Johannes Ballé +1
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 origin…
End-to-end Optimized Image Compression
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. The transforms are constr…
Image Denoising with Kernels based on Natural Image Relations
Valero Laparra, Juan Gutiérrez, Gustavo Camps-Valls +1
A successful class of image denoising methods is based on Bayesian approaches working in wavelet representations. However, analytical estimates can be obtained only for particular…