1,495 Hits in 2.9 sec

Convolutional Neural Networks Deceived by Visual Illusions [article]

Alexander Gomez-Villa, Adrián Martín, Javier Vazquez-Corral, Marcelo Bertalmío
2018 arXiv   pre-print
Visual illusions teach us that what we see is not always what it is represented in the physical world. Its special nature make them a fascinating tool to test and validate any new vision model proposed. In general, current vision models are based on the concatenation of linear convolutions and non-linear operations. In this paper we get inspiration from the similarity of this structure with the operations present in Convolutional Neural Networks (CNNs). This motivated us to study if CNNs
more » ... for low-level visual tasks are deceived by visual illusions. In particular, we show that CNNs trained for image denoising, image deblurring, and computational color constancy are able to replicate the human response to visual illusions, and that the extent of this replication varies with respect to variation in architecture and spatial pattern size. We believe that this CNNs behaviour appears as a by-product of the training for the low level vision tasks of denoising, color constancy or deblurring. Our work opens a new bridge between human perception and CNNs: in order to obtain CNNs that better replicate human behaviour, we may need to start aiming for them to better replicate visual illusions.
arXiv:1811.10565v1 fatcat:fcyeob5wjfanpnk23wreqese5a

Perceptual Color Characterization of Cameras

Javier Vazquez-Corral, David Connah, Marcelo Bertalmío
2014 Sensors  
This is why Javier Vazquez-Corral and Marcelo Bertalmío are with the Department of Information and Communications Technologies, Universitat Pompeu Fabra.  ... 
doi:10.3390/s141223205 pmid:25490586 pmcid:PMC4299059 fatcat:zetxrya66nc2zorl6q2ssamy5i

Synthesizing Visual Illusions Using Generative Adversarial Networks [article]

Alexander Gomez-Villa, Adrian Martín, Javier Vazquez-Corral, Jesús Malo, Marcelo Bertalmío
2019 arXiv   pre-print
Visual illusions are a very useful tool for vision scientists, because they allow them to better probe the limits, thresholds and errors of the visual system. In this work we introduce the first ever framework to generate novel visual illusions with an artificial neural network (ANN). It takes the form of a generative adversarial network, with a generator of visual illusion candidates and two discriminator modules, one for the inducer background and another that decides whether or not the
more » ... ate is indeed an illusion. The generality of the model is exemplified by synthesizing illusions of different types, and validated with psychophysical experiments that corroborate that the outputs of our ANN are indeed visual illusions to human observers. Apart from synthesizing new visual illusions, which may help vision researchers, the proposed model has the potential to open new ways to study the similarities and differences between ANN and human visual perception.
arXiv:1911.09599v1 fatcat:bsxyisecs5fnjlww2zlfe3tuwq

Simultaneous Blind Gamma Estimation

Javier Vazquez-Corral, Marcelo Bertalmio
2015 IEEE Signal Processing Letters  
Recently, Vazquez-Corral and Bertalmío [13] proposed a color stabilization method which is based on the imaging formation model presented by Bianco et al. [1] .  ...  Following this model, Vazquez-Corral and Bertalmío represent the pixel values as:   R G B   p1 =   A 1   R G B   p   1 γ 1 ;   R G B   p2 =   A 2   R G B   p   1 γ 2 (2) where A  ... 
doi:10.1109/lsp.2015.2396299 fatcat:pl3vk2bbvbdy3n4mn54dfean64

Fusion-based Variational Image Dehazing

Adrian Galdran, Javier Vazquez-Corral, David Pardo, Marcelo Bertalmio
2016 IEEE Signal Processing Letters  
We propose a novel image dehazing technique based on the minimization of two energy functionals and a fusion scheme to combine the output of both optimizations. The proposed Fusion-based Variational Image Dehazing (FVID) method is a spatially varying image enhancement process that first minimizes a previously proposed variational formulation that maximizes contrast and saturation on the hazy input. The iterates produced by this minimization are kept, and a second energy that shrinks faster
more » ... sity values of well-contrasted regions is minimized, allowing to generate a set of Difference-of-Saturations (DiffSat) maps by observing the shrinking rate. The iterates produced in the first minimization are then fused with these DiffSat maps to produce a haze-free version of the degraded input. The FVID method does not rely on a physical model from which to estimate a depth map, nor it needs a training stage on a database of human-labeled examples. Experimental results on a wide set of hazy images demonstrate that FVID better preserves the image structure on close-by regions that are less affected by fog, and it successfully compares with other current methods in the task of removing haze degradation from far-away regions.
doi:10.1109/lsp.2016.2643168 fatcat:dvbixycvqbhivfbhu54cignccm

Spectral Sharpening of Color Sensors: Diagonal Color Constancy and Beyond

Javier Vazquez-Corral, Marcelo Bertalmío
2014 Sensors  
Vazquez-Corral et al.  ...  Building upon Philipona and O'Regan's model, Vazquez-Corral et al.  ... 
doi:10.3390/s140303965 pmid:24577523 pmcid:PMC4003926 fatcat:zzphrex2zrbaplztv4zzop326m

Enhanced Variational Image Dehazing

Adrian Galdran, Javier Vazquez-Corral, David Pardo, Marcelo Bertalmío
2015 SIAM Journal of Imaging Sciences  
Images obtained under adverse weather conditions, such as haze or fog, typically exhibit low contrast and faded colors, which may severely limit the visibility within the scene. Unveiling the image structure under the haze layer and recovering vivid colors out of a single image remains a challenging task, since the degradation is depth-dependent and conventional methods are unable to overcome this problem. In this work, we extend a well-known perception-inspired variational framework for single
more » ... image dehazing. Two main improvements are proposed. First, we replace the value used by the framework for the grey-world hypothesis by an estimation of the mean of the clean image. Second, we add a set of new terms to the energy functional for maximizing the inter-channel contrast. Experimental results show that the proposed Enhanced Variational Image Dehazing (EVID) method outperforms other state-of-the-art methods both qualitatively and quantitatively. In particular, when the illuminant is uneven, our EVID method is the only one that recovers realistic colors, avoiding the appearance of strong chromatic artifacts.
doi:10.1137/15m1008889 fatcat:axfgft5xjjhnxid6eohvw4ka64

Gamut Mapping through Perceptually-Based Contrast Reduction [chapter]

Syed Waqas Zamir, Javier Vazquez-Corral, Marcelo Bertalmío
2014 Lecture Notes in Computer Science  
In this paper we present a spatial gamut mapping algorithm that relies on a perceptually-based variational framework. Our method adapts a well-known image energy functional whose minimization leads to image enhancement and contrast modification. We show how by varying the importance of the contrast term in the image functional we are able to perform gamut reduction. We propose an iterative scheme that allows our algorithm to successfully map the colors from the gamut of the original image to a
more » ... iven destination gamut while preserving the colors' perception and texture close to the original image. Both subjective and objective evaluation validate the promising results achieved via our proposed framework.
doi:10.1007/978-3-642-53842-1_1 fatcat:5dzyy75cajaxxhwingtwul3bqa

Physical-based optimization for non-physical image dehazing methods

Javier Vazquez-Corral, Graham Finlayson, Marcelo Bertalmio
2020 Optics Express  
Images captured under hazy conditions (e.g. fog, air pollution) usually present faded colors and loss of contrast. To improve their visibility, a process called image dehazing can be applied. Some of the most successful image dehazing algorithms are based on image processing methods but do not follow any physical image formation model, which limits their performance. In this paper, we propose a post-processing technique to alleviate this handicap by enforcing the original method to be
more » ... with a popular physical model for image formation under haze. Our results improve upon those of the original methods qualitatively and according to several metrics, and they have also been validated via psychophysical experiments. These results are particularly striking in terms of avoiding over-saturation and reducing color artifacts, which are the most common shortcomings faced by image dehazing methods.
doi:10.1364/oe.383799 pmid:32225542 fatcat:swoayniigvgfzmhlhnvytcli6e

A Variational Framework for Single Image Dehazing [chapter]

Adrian Galdran, Javier Vazquez-Corral, David Pardo, Marcelo Bertalmío
2015 Lecture Notes in Computer Science  
Images captured under adverse weather conditions, such as haze or fog, typically exhibit low contrast and faded colors, which may severely limit the visibility within the scene. Unveiling the image structure under the haze layer and recovering vivid colors out of a single image remains a challenging task, since the degradation is depth-dependent and conventional methods are unable to handle this problem. We propose to extend a well-known perception-inspired variational framework [1] for the
more » ... of single image dehazing. The main modification consists on the replacement of the value used by this framework for the grey-world hypothesis by an estimation of the mean of the clean image. This allows us to devise a variational method that requires no estimate of the depth structure of the scene, performing a spatially-variant contrast enhancement that effectively removes haze from far away regions. Experimental results show that our method competes well with other stateof-the-art methods in typical benchmark images, while outperforming current image dehazing methods in more challenging scenarios.
doi:10.1007/978-3-319-16199-0_18 fatcat:nzv42pjcwbdjnmz4alv6wjrfl4

Dilatación transparietohepática de estenosis biliar benigna: experiencia de 5 años

María Diez Tabernilla, Eduardo Lobo Martínez, Javier Nuño Vazquez-Garza, Javier Blázquez Sánchez, Juan Sánchez Corral, Virgilio Fresneda Moreno
2010 Cirugia Española  
informa ció n del artí culo Historia del artículo: Recibido el 26 de marzo de 2009 Aceptado el 31 de marzo de 2010 Palabras clave: Estenosis biliar Dilatació n percutá nea transparietohepá tica Dilatació n con baló n Anastomosis bilioenté rica r e s u m e n Objetivo: Valorar los resultados de la dilatació n percutá nea transparietohepá tica de las estenosis biliares benignas durante un período de 5 añ os. Diseñ o: Estudio retrospectivo para evaluar la té cnica, las complicaciones y los
more » ... s clínicos, analíticos y radioló gicos. Pacientes: Se recogieron datos de 13 pacientes diagnosticados de estenosis biliar benigna que se trataron mediante dilatació n percutá nea en nuestro centro entre los añ os 2002-2006. Se excluyó a los pacientes diagnosticados de enfermedad maligna y a aquellos pacientes a los que se les colocó una pró tesis. Siete de los pacientes han sido receptores de trasplante hepá tico. Un paciente había recibido dilatació n endoscó pica en 2 ocasiones con persistencia de la estenosis. Resultados: Se comprobó mejoría clínica y radioló gica en el 60% de los casos y analítica en el 69% de los casos (el 61% de normalizació n). El 30% de los casos presentó reestenosis, de los que el 50% fueron subsidiarios de rescate mediante redilatació n. Las complicaciones que se presentaron (30,7%) se resolvieron de forma conservadora. No se observaron diferencias significativas entre el grupo de trasplante y el grupo sin trasplante. Conclusiones: La dilatació n de las estenosis benignas de la vía biliar por vía transparietohepá tica es una té cnica bastante segura, tiene una alta tasa de resolució n a medio plazo y permite evitar la cirugía en má s de un 75% de los pacientes. Los resultados deben confirmarse en muestras mayores. & 2009 AEC. Publicado por Elsevier Españ a, S.L. Todos los derechos reservados. Transparieto-hepatic dilation of benign biliary stenosis: 5 years experience Keywords: Biliary stenosis Transparieto-hepatic percutaneous dilation a b s t r a c t Objective: To assess the results of percutaneous transparieto-hepatic dilation of benign biliary stenosis achieved over a period of 5 years. Design: A retrospective study to assess the technique, complications and the clinical, analytical and radiology results.
doi:10.1016/j.ciresp.2010.03.044 pmid:20510398 fatcat:uhcasn6kyrfnjepz642kmmpcdq

Matching visual induction effects on screens of different size

Trevor Canham, Javier Vazquez-Corral, Elise Mathieu, Marcelo Bertalmío
2021 Journal of Vision  
, Mathieu, & Bertalmío Canham, Vazquez-Corral, Mathieu, & Bertalmío  ...  ., 2007) and in a color opponent color space like CIELAB (Zamir, Vazquez-Corral & Bertalmío, 2017) , and the results showed that the LHE method has several good properties: (1) It has a very good local  ... 
doi:10.1167/jov.21.6.10 pmid:34144607 pmcid:PMC8237091 fatcat:27g7jk3wrjervhnf4fqaarzln4

Gamut mapping for visual attention retargeting

Javier Vazquez-Corral, Marcelo Bertalmío
2017 Final program and proceedings (Color and Imaging Conference)  
Author Biography Javier Vazquez-Corral received the Ph.D. degree in computer science from the Universitat Autònoma de Barcelona, Bellaterra, Spain, in 2011.  ... 
doi:10.2352/issn.2169-2629.2017.25.313 fatcat:homrvhdsbze3zmxpf6wqkpv3de

Color matching images with unknown non-linear encodings

Raquel Gil Rodriguez, Javier Vazquez-Corral, Marcelo Bertalmio
2020 IEEE Transactions on Image Processing  
One is the method of Vazquez-Corral and Bertalmío [26] , that relies on finding a sufficiently large number of achromatic matches among source and reference.  ...  Vazquez-Corral and Bertalmío [24] proposed a color stabilization algorithm that consists of estimating a power law (γ value) for each of the images, and a single 3 × 3 matrix, to color match the source  ... 
doi:10.1109/tip.2020.2968766 pmid:32011253 fatcat:ek3poa5jvveuxisykycuwuymiy

Spatial gamut mapping among non-inclusive gamuts

Javier Vazquez-Corral, Marcelo Bertalmío
2018 Journal of Visual Communication and Image Representation  
Gamut mapping transforms the color gamut of an image to that of a target device. Two cases are usually considered: gamut reduction (target gamut smaller than source gamut), and gamut extension (target gamut larger than the source gamut). Less attention is devoted to the more general case, when neither gamut is fully included in the other. In this work we unify and expand two recent methods for gamut extension and reduction, so as to simultaneously perform both forms of gamut mapping in
more » ... regions of the same image without introducing color artifacts or halos. We demonstrate the usefulness of this approach for the traditional gamut mapping problem, and also how the proposed method can be used to adapt the color palette of an image so that it is closer to that of a given reference image. Results are compared with the state-of-the-art and validated through user tests and objective metrics.
doi:10.1016/j.jvcir.2018.05.012 fatcat:ga7q7et275f57ng43t5beaax7m
« Previous Showing results 1 — 15 out of 1,495 results