Ara es mostren els items 1-20 de 43

  • Accelerating super-resolution for 4K upscaling 

    Pérez-Pellitero, Eduardo; Salvador, Jordi; Ruiz Hidalgo, Javier; Rosenhahn, Bodo (Institute of Electrical and Electronics Engineers (IEEE), 2015)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    This paper presents a fast Super-Resolution (SR) algorithm based on a selective patch processing. Motivated by the observation that some regions of images are smooth and unfocused and can be properly upscaled with fast ...
  • Advanced visual rendering, gesture-based interaction and distributed delivery for immersive and interactive media services 

    Niamut, O.A.; Kochale, A.; Ruiz Hidalgo, Javier; Macq, J.; Kienast, G. (2011)
    Text en actes de congrés
    Accés obert
    The media industry is currently being pulled in the often-opposing directions of increased realism (high resolution, stereoscopic, large screen) and personalisation (selection and control of content, availability on many ...
  • An epipolar-constrained prior for efficient search in multi-view scenarios 

    Bosch, Ignacio; Salvador, Jordi; Pérez-Pellitero, Eduardo; Ruiz Hidalgo, Javier (Institute of Electrical and Electronics Engineers (IEEE), 2014)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    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 ...
  • Antipodally invariant metrics for fast regression-based super-resolution 

    Pérez-Pellitero, Eduardo; Salvador, Jordi; Ruiz Hidalgo, Javier; Rosenhahn, Bodo (2016-03-31)
    Article
    Accés obert
    Dictionary-based super-resolution (SR) algorithms usually select dictionary atoms based on the distance or similarity metrics. Although the optimal selection of the nearest neighbors is of central importance for such ...
  • AV renderer with enhanced processing with integration of scripting language. FascinatE deliverable D5.1.3 

    Kochale, A.; Borsum, M.; Spille, J.; Kropp, H.; Ruiz Hidalgo, Javier; Suau Cuadros, Xavier; Gil, Albert; Macq, J.; Oldfield, Rob (2012-09-03)
    Report de recerca
    Accés restringit per acord de confidencialitat
  • Bayesian region selection for adaptive dictionary-based Super-Resolution 

    Pérez-Pellitero, Eduardo; Salvador, Jordi; Ruiz Hidalgo, Javier; Rosenhahn, Bodo (2013)
    Comunicació de congrés
    Accés obert
    The performance of dictionary-based super-resolution (SR) strongly depends on the contents of the training dataset. Nevertheless, many dictionary-based SR methods randomly select patches from of a larger set of training ...
  • Comparison of MPEG-7 descriptors for long term selection of reference frames 

    Ruiz Hidalgo, Javier; Salembier Clairon, Philippe Jean (2009)
    Comunicació de congrés
    Accés obert
    During the last years, the amount of multimedia content has greatly increased. This has multiplied the need of efficient compression of the content but also the ability to search, retrieve, browse, or filter it. Generally, ...
  • Depth map coding based on a optimal hierarchical region representation 

    Maceira Duch, Marc; Ruiz Hidalgo, Javier; Morros Rubió, Josep Ramon (Institute of Electrical and Electronics Engineers (IEEE), 2012)
    Text en actes de congrés
    Accés restringit per decisió de l'autor
    Multiview color information used jointly with depth maps is a widespread technique for 3D video. Using this depth information, 3D functionalities such as free view point video can be provided by means of depth-image-based ...
  • Depth map compression via 3D region-based representation 

    Maceira, Marc; Morros Rubió, Josep Ramon; Ruiz Hidalgo, Javier (2016-07-21)
    Article
    Accés obert
    In 3D video, view synthesis is used to create new virtual views between encoded camera views. Errors in the coding of the depth maps introduce geometry inconsistencies in synthesized views. In this paper, a new 3D ...
  • Detecting end-effectors on 2.5D data using geometric deformable models: application to human pose estimation 

    Suau Cuadros, Xavier; Ruiz Hidalgo, Javier; Casas Pla, Josep Ramon (2013-03)
    Article
    Accés restringit per política de l'editorial
    End-effectors are usually related to the location of limbs, and their reliable detection enables robust body tracking as well as accurate pose estimation. Recent innovation in depth cameras has re-stated the pose estimation ...
  • Dissemination and exploitation plan (including standardisation). FascinatE deliverable D7.1.3b 

    Thomas, G.; Masetti, Marco; Niamut, O.A.; Kienast, G.; Thallinger, Georg; Schreer, Oliver; Kochale, A.; Ruiz Hidalgo, Javier; Oldfield, Rob; Macq, J. (2012-02-16)
    Report de recerca
    Accés restringit per acord de confidencialitat
  • Elaboració de materials transversals per a l'aprenentatge actiu de les matèries de processat d'imatge i vídeo pels graus de sistemes audiovisuals i de telecomunicacions 

    Vilaplana Besler, Verónica; Casas Pla, Josep Ramon; Gasull Llampallas, Antoni; Marqués Acosta, Fernando; Morros Rubió, Josep Ramon; Pardàs Feliu, Montse; Ruiz Hidalgo, Javier; Salembier Clairon, Philippe Jean (Universitat Politècnica de Catalunya. Institut de Ciències de l'Educació, 2013-02-08)
    Text en actes de congrés / Comunicació de congrés
    Accés obert
    La finalitat del projecte ha estat promoure la col·laboració i coordinació entre les diverses assignatures de processat d'imatge i vídeo impartides per professors del Departament de TSC, als graus de telecomunicacions ...
  • FascinatE D1.1.1 End user, production and hardware and networking requirements 

    Macq, J.; Juhlin, O.; Önnevall, E.; Perry, M.; Ruiz Hidalgo, Javier; Casas Pla, Josep Ramon; Suau Cuadros, Xavier; Gibb, A.; Niamut, O.A.; Prins, M.J.; Zoric, G.; Engström, A. (2010-09-01)
    Report de recerca
    Accés obert
    This document defines the overall requirements that the FascinatE system should meet. The deliverable proposes three scenarios, depending on the configuration and functionality of the complete delivery chain, where to ...
  • FascinatE D3.1.1 Survey of Metadata and Knowledge for Automated Scripting 

    Thomas, G.; Schreer, Oliver; Oldfield, Rob; Shirley, Ben; Niamut, O.A.; Poggi, A.; Masetti, M.; Bailer, W; Kaiser, R.; Engstrom, A.; Ruiz Hidalgo, Javier; Kochale, A.; Macq, J.; Rondao Alface, P.; Verzijp, N. (2010-11-30)
    Report de recerca
    Accés obert
    This document defines the various types of metadata in the FascinatE system and discusses representation requirements and candidate formats. The document considers various types of metadata describing capture, production, ...
  • FascinatE D5.1.1 AV renderer specification and basic characterisation of audience interaction 

    Borsum, M.; Spille, J.; Kochale, A.; Önnevall, E.; Zoric, G.; Ruiz Hidalgo, Javier (2010-09-01)
    Report de recerca
    Accés obert
    This document presents the renderer specification and basic characterisation of audience interaction for the FascinatE system.
  • FascinatE Newsletter 1 

    Ruiz Hidalgo, Javier; Suau Cuadros, Xavier; Thallinger, Georg; Shirley, Ben (2010-10-01)
    Report de recerca
    Accés obert
    This FascinatE newsletter explains how gesture recognition will be used in the FascinatE system, how our first test shoot went at a Premier League football match, and explains about up and coming events.
  • Fast and robust edge extraction in unorganized point clouds 

    Bazazian, Dena; Casas Pla, Josep Ramon; Ruiz Hidalgo, Javier (Institute of Electrical and Electronics Engineers (IEEE), 2015)
    Comunicació de congrés
    Accés restringit per política de l'editorial
    Edges provide important visual information in scene surfaces. The need for fast and robust feature extraction from 3D data is nowadays fostered by the widespread availability of cheap commercial depth sensors and multi-camera ...
  • Fast super-resolution via dense local training and inverse regressor search 

    Pérez-Pellitero, Eduardo; Salvador, Jordi; Torres-Xirau, Iban; Ruiz Hidalgo, Javier; Rosenhahn, Bodo (2014-11-01)
    Article
    Accés obert
    Regression-based Super-Resolution (SR) addresses the upscaling problem by learning a mapping function (i.e. regressor) from the low-resolution to the high-resolution manifold. Under the locally linear assumption, this ...
  • Fast super-resolution via dense local training and inverse regressor search 

    Pérez Pellitero, Eduardo; Salvador, Jordi; Torres Xirau, Iban; Ruiz Hidalgo, Javier; Rosenhahn, Bodo (Springer, 2014)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    Regression-based Super-Resolution (SR) addresses the upscaling problem by learning a mapping function (i.e. regressor) from the low-resolution to the high-resolution manifold. Under the locally linear assumption, this ...
  • Format-agnostic approach for production, delivery and rendering of immersive media 

    Thallinger, Georg; Shirley, Ben; Schreer, Oliver; Thomas, Graham; Niamut, O.A.; Macq, J.; Kochale, A.; Batke, J.M.; Ruiz Hidalgo, Javier; Oldfield, Rob (2011)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    The media industry is currently being pulled in the often-opposing directions of increased realism (high resolution, stereoscopic, large screen) and personalisation (selection and control of content, availability on many ...