Time filter

Source Type

Perez-Pellitero E.,Leibniz University of Hanover | Salvador J.,Technicolor RandI Hanover | Ruiz-Hidalgo J.,Polytechnic University of Catalonia | Rosenhahn B.,Leibniz University of Hanover
2016 IEEE Winter Conference on Applications of Computer Vision, WACV 2016

Recent research in piecewise linear regression for Super-Resolution has shown the positive impact of training regressors with densely populated clusters whose datapoints are tight in the Euclidean space. In this paper we further research how to improve the locality condition during the training of regressors and how to better select them during testing time. We study the characteristics of the metrics best suited for the piecewise regression algorithms, in which comparisons are usually made between normalized vectors that lie on the unitary hypersphere. Even though Euclidean distance has been widely used for this purpose, it is suboptimal since it does not handle antipodal points (i.e. diametrically opposite points) properly, as vectors with same module and angle but opposite directions are, for linear regression purposes, identical. Therefore, we propose the usage of antipodally invariant metrics and introduce the Half Hypersphere Confinement (HHC), a fast alternative to Multidimensional Scaling (MDS) that allows to map antipodally invariant distances in the Euclidean space with very little approximation error By doing so, we enable the usage of fast search structures based on Euclidean distances without undermining their speed gains with complex distance transformations. The performance of our method, which we named HHC Regression (HHCR), applied to SuperResolution (SR) improves both in quality (PSNR) and it is faster than any other state-of-the-art method. Additionally, under an application-agnostic interpretation of our regression framework, we also test our algorithm for denoising and depth upscaling with promising results. © 2016 IEEE. Source

Salvador J.,Technicolor RandI Hanover | Perez-Pellitero E.,Technicolor RandI Hanover
Proceedings of the IEEE International Conference on Computer Vision

This paper presents a fast, high-performance method for super resolution with external learning. The first contribution leading to the excellent performance is a bimodal tree for clustering, which successfully exploits the antipodal invariance of the coarse-to-high-res mapping of natural image patches and provides scalability to finer partitions of the underlying coarse patch space. During training an ensemble of such bimodal trees is computed, providing different linearizations of the mapping. The second and main contribution is a fast inference algorithm, which selects the most suitable mapping function within the tree ensemble for each patch by adopting a Local Naive Bayes formulation. The experimental validation shows promising scalability properties that reflect the suitability of the proposed model, which may also be generalized to other tasks. The resulting method is beyond one order of magnitude faster and performs objectively and subjectively better than the current state of the art. © 2015 IEEE. Source

Salvador J.,Technicolor RandI Hanover | Rivero D.,Technicolor RandI Hanover | Rivero D.,Polytechnic University of Catalonia | Kochale A.,Technicolor RandI Hanover | Ruiz-Hidalgo J.,Polytechnic University of Catalonia
Proceedings - International Conference on Pattern Recognition

This paper presents a variational framework for obtaining super-resolved video-sequences, based on the observation that reconstruction-based Super-Resolution (SR) algorithms are limited by two factors: registration exactitude and Point Spread Function (PSF) estimation accuracy. To minimize the impact of the first limiting factor, a small-scale linear in-painting algorithm is proposed to provide smooth SR video frames. To improve the second limiting factor, a fast PSF local estimation and total variation-based denoising is proposed. Experimental results reflect the improvements provided by the proposed method when compared to classic SR approaches. © 2012 ICPR Org Committee. Source

Bosch I.,Technicolor RandI Hanover | Bosch I.,Polytechnic University of Catalonia | Salvador J.,Technicolor RandI Hanover | Perez-Pellitero E.,Technicolor RandI Hanover | Ruiz-Hidalgo J.,Polytechnic University of Catalonia
European Signal Processing Conference

In this paper we propose a novel framework for fast exploitation of multi-view cues with applicability in different image processing problems. In order to bring our proposed framework into practice, an epipolar-constrained prior is presented, onto which a random search algorithm is proposed to find good matches among the different views of the same scene. This algorithm includes a generalization of the local coherency in 2D images for multi-view wide-baseline cases. Experimental results show that the geometrical constraint allows a faster initial convergence when finding good matches. We present some applications of the proposed framework on classical image processing problems. © 2014 EURASIP. Source

Salvador J.,Technicolor RandI Hanover | Perez-Pellitero E.,Technicolor RandI Hanover | Kochale A.,Technicolor RandI Hanover
2014 IEEE International Conference on Image Processing, ICIP 2014

We present a noise-aware single-image super-resolution (SI-SR) algorithm, which automatically cancels additive noise while adding detail learned from lower-resolution scales. In contrast with most SI-SR techniques, we do not assume the input image to be a clean source of examples. Instead, we adapt the recent and efficient in-place cross-scale self-similarity prior for both learning fine detail examples and reducing image noise. Our experiments show a promising performance, despite the relatively simple algorithm. Both objective evaluations and subjective validations show clear quality improvements when upscaling noisy images. © 2014 IEEE. Source

Discover hidden collaborations