Now showing items 1-20 of 25

    • 3D pose estimation in complex environments 

      Peñate Sánchez, Adrián (Universitat Politècnica de Catalunya, 2017-04-07)
      Doctoral thesis
      Open Access
      Although there has been remarkable progress in the pose estimation literature, there are still a number of limitations when existing algorithms must be applied in everyday applications, especially in uncontrolled environments. ...
    • 3D pose estimation using convolutional neural networks 

      Rubio Romano, Antonio (Universitat Politècnica de Catalunya, 2015-10)
      Master thesis
      Open Access
      The present Master Thesis describes a new Pose Estimation method based on Convolutional Neural Networks (CNN). This method divides the three-dimensional space in several regions and, given an input image, returns the ...
    • A Human Shape-Motion Predictor with Deep Learning 

      Romero Mérida, Antonio (Universitat Politècnica de Catalunya, 2019-04-24)
      Master thesis
      Open Access
      The objective of this work is to obtain an end-to-end solution which predicts human motion and shape from a given video by extracting its pose in the Wild. Given incomplete human motion sequences our goal is to predict and ...
    • Bridging the gap between reconstruction and synthesis 

      Pumarola Peris, Albert (Universitat Politècnica de Catalunya, 2021-10-13)
      Doctoral thesis
      Open Access
      3D reconstruction and image synthesis are two of the main pillars in computer vision. Early works focused on simple tasks such as multi-view reconstruction and texture synthesis. With the spur of Deep Learning, the field ...
    • CNNs for electron microscopy segmentation 

      García-Amorena García, Pablo (Universitat Politècnica de Catalunya / École Polytechnique Fédérale de Lausanne, 2013)
      Bachelor thesis
      Restricted access - author's decision
      Covenantee:   École polytechnique fédérale de Lausanne
      In the framework of Biomedicine, mitochondria are known to play an important role in neural function. Recent studies show mitochondrial morphology to be crucial to cellular physiology and synaptic function, and a link ...
    • Combining geometric and appearance priors for pose recovery 

      Seradel Domingo, Eduard (Universitat Politècnica de Catalunya, 2009-09)
      Master thesis
      Restricted access - author's decision
      Estimar la pose (rotació i translació) de la càmera a partir dels punts d'interés de l'escena 3D i punts de la imatge 2D és un problema ben resolt en el cas que es coneguin les correspondències entre ells. No obstant, quan ...
    • Enhancing low-level features with mid-level cues 

      Trulls Fortuny, Eduard (Universitat Politècnica de Catalunya, 2015-02-20)
      Doctoral thesis
      Open Access
      Local features have become an essential tool in visual recognition. Much of the progress in computer vision over the past decade has built on simple, local representations such as SIFT or HOG. SIFT in particular shifted ...
    • Enhancing scene text recognition with visual context information 

      Sabir, Ahmed (Universitat Politècnica de Catalunya, 2020-11-10)
      Doctoral thesis
      Open Access
      This thesis addresses the problem of improving text spotting systems, which aim to detect and recognize text in unrestricted images (e.g. a street sign, an advertisement, a bus destination, etc.). The goal is to improve ...
    • Fashion discovery : a computer vision approach 

      Rubio Romano, Antonio (Universitat Politècnica de Catalunya, 2021-07-23)
      Doctoral thesis
      Open Access
      Performing semantic interpretation of fashion images is undeniably one of the most challenging domains for computer vision. Subtle variations in color and shape might confer different meanings or interpretations to an ...
    • Few-shot 3D reconstruction of body parts with deep neural networks 

      Ramon Maldonado, Eduard (Universitat Politècnica de Catalunya, 2022-09-15)
      Doctoral thesis
      Open Access
      (English) In this thesis, we study the problem of reconstructing objects from a concrete category in 3D when few images are available as input, i.e. less than 10. We apply our findings to digitalizing human body parts such ...
    • Geometric computer vision meets deep learning for autonomous driving applications 

      García López, Javier (Universitat Politècnica de Catalunya, 2021-05-17)
      Doctoral thesis
      Open Access
      This dissertation intends to provide theoretical and practical contributions on the development of deep learning algorithms for autonomous driving applications. The research is motivated by the need of deep neural networks ...
    • Human motion dataset in the wild (MAT) 

      Coll Ribes, Gabriel (Universitat Politècnica de Catalunya, 2019-03-07)
      Bachelor thesis
      Open Access
      The popularity of wearable cameras is steadily increasing, both for entertainment and productivity purposes. Understanding the footage and inferring the body pose of the camera wearer can be of great importance in many ...
    • Implementación en Android de un algoritmo que calcula la pose de la cámara respecto de un objeto 

      Garré Vicente, Sinuhé (Universitat Politècnica de Catalunya, 2015-06)
      Master thesis (pre-Bologna period)
      Restricted access - author's decision
      El presente proyecto tiene como objetivo principal la implementación de una aplicación para dispositivos Android. Esta aplicación, permite calcular en tiempo real, la pose de la cámara respecto a un objeto. La posición ...
    • Implementation of a 3D pose estimation algorithm 

      Riba Pi, Edgar (Universitat Politècnica de Catalunya, 2015-06)
      Master thesis
      Open Access
    • Learning to run naturally: guiding policies with the Spring-Loaded Inverted Pendulum 

      Ordoñez Apraez, Daniel Felipe (Universitat Politècnica de Catalunya, 2021-04-28)
      Master thesis
      Open Access
      Covenantee:   Universitat de Barcelona / Universitat Rovira i Virgili
      In this work, we proposed a new approach for learning legged locomotion for any legged robot, in the sagittal plane, by using a combination of classical control techniques and reinforcement learning. Specifically, we use ...
    • Lidar-based scene understanding for autonomous driving using deep learning 

      Vaquero Gómez, Víctor (Universitat Politècnica de Catalunya, 2020-02-25)
      Doctoral thesis
      Open Access
      With over 1.35 million fatalities related to traffic accidents worldwide, autonomous driving was foreseen at the beginning of this century as a feasible solution to improve security in our roads. Nevertheless, it is meant ...
    • Modeling and reconstruction of 3D humans 

      Corona Puyane, Enric (Universitat Politècnica de Catalunya, 2023-11-16)
      Doctoral thesis
      Open Access
      (English) Understanding humans in images has been a long-standing goal in Computer Vision. Recently, modelling and generation of virtual humans has become a popular area of research spurred by the success of deep learning, ...
    • Modeling and reconstruction of 3D humans under context 

      Ugrinovic Kehdy, Nicolas (Universitat Politècnica de Catalunya, 2025-04-04)
      Doctoral thesis
      Open Access
      (English) The study of human's and their behavior through the analysis of images and videos has long been a central topic in Computer Vision. The reconstruction and modeling of human behavior have garnered increasing ...
    • Non-Rigid Structure from Motion for Complex Motion 

      Molina Mellado, Sergi (Universitat Politècnica de Catalunya, 2016-09-05)
      Master thesis
      Open Access
      Recovering deformable 3D motion from temporal 2D point tracks in a monocular video is an open problem with many everyday applications throughout science and industry, or the new augmented reality. Recently, several techniques ...
    • Reconocimiento de árboles mediante redes neuronales convolucionales 

      Génova Tesoro, Ana; Gironès Bedós, Xavier (Universitat Politècnica de Catalunya, 2016-06-23)
      Bachelor thesis
      Open Access
      Elaboración de un programa que sea capaz de reconocer una especie biológica (árbol en principio) a través de una foto tomada por un usuario. Posibilidad de vincular el programa a una App para Smartphone.