Exploració per autor "Pumarola Peris, Albert"
Ara es mostren els items 1-20 de 23
-
3DPeople: modeling the geometry of dressed humans
(2019)
Text en actes de congrés
Accés obertRecent advances in 3D human shape estimation build upon parametric representations that model very well the shape of the naked body, but are not appropriate to represent the clothing geometry. In this paper, we present an ... -
Attention deep learning based model for predicting the 3D Human Body Pose using the Robot Human Handover Phases
(2021)
Text en actes de congrés
Accés obertThis work proposes a human motion prediction model for handover operations. We use in this work, the different phases of the handover operation to improve the human motion predictions. Our attention deep learning based ... -
Bridging the gap between reconstruction and synthesis
(2021-10-13)
Tesi
Accés obert3D 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 ... -
C-Flow: conditional generative flow models for images and 3D point clouds
(Institute of Electrical and Electronics Engineers (IEEE), 2020)
Text en actes de congrés
Accés obertFlow-based generative models have highly desirable properties like exact log-likelihood evaluation and exact latent-variable inference, however they are still in their infancy and have not received as much attention as ... -
Context-aware human motion prediction
(2020)
Comunicació de congrés
Accés obertThe problem of predicting human motion given a sequence of past observations is at the core of many applications in robotics and computer vision. Current state-of-the-art formulates this problem as a sequence-to-sequence ... -
Control de comportament d'un robot de servei per mitjà d'una arquitectura cognitiva
(Universitat Politècnica de Catalunya, 2014-06-30)
Projecte/Treball Final de Carrera
Accés obert[CATALÀ] Aquest treball planteja nou enfocament per la resolució de tasques complexes en la robòtica de servei. Amb aquest objectiu, s'ha implementat una arquitectura cognitiva basada en Soar. Aquesta arquitectura ha estat ... -
D-NeRF: neural radiance fields for dynamic scenes
(Institute of Electrical and Electronics Engineers (IEEE), 2021)
Text en actes de congrés
Accés obertNeural rendering techniques combining machine learning with geometric reasoning have arisen as one of the most promising approaches for synthesizing novel views of a scene from a sparse set of images. Among these, stands ... -
Enhancing egocentric 3D pose estimation with third person views
(Elsevier, 2023-06)
Article
Accés obertWe propose a novel approach to enhance the 3D body pose estimation of a person computed from videos captured from a single wearable camera. The main technical contribution consists of leveraging high-level features linking ... -
Ganhand: predicting human grasp affordances in multi-object scenes
(2020)
Comunicació de congrés
Accés obertThe rise of deep learning has brought remarkable progress in estimating hand geometry from images where the hands are part of the scene. This paper focuses on a new problem not explored so far, consisting in predicting how ... -
GANimation: anatomically-aware facial animation from a single image
(Springer, 2018)
Text en actes de congrés
Accés obertRecent advances in Generative Adversarial Networks (GANs) have shown impressive results for task of facial expression synthesis. The most successful architecture is StarGAN, that conditions GANs' generation process with ... -
GANimation: one-shot anatomically consistent facial animation
(2019-01-01)
Article
Accés obertRecent advances in generative adversarial networks (GANs) have shown impressive results for the task of facial expression synthesis. The most successful architecture is StarGAN (Choi et al. in CVPR, 2018), that conditions ... -
Geometry-aware network for non-rigid shape prediction from a single view
(Institute of Electrical and Electronics Engineers (IEEE), 2018)
Text en actes de congrés
Accés obertWe propose a method for predicting the 3D shape of a deformable surface from a single view. By contrast with previous approaches, we do not need a pre-registered template of the surface, and our method is robust to the ... -
H3D-Net: Few-shot high-fidelity 3D head reconstruction
(Computer Vision Foundation, 2021)
Comunicació de congrés
Accés obertRecent learning approaches that implicitly represent surface geometry using coordinate-based neural representations have shown impressive results in the problem of multi-view 3D reconstruction. The effectiveness of these ... -
Optimization of common computer vision algorithms : beating OpenCV face detector
(Universitat Politècnica de Catalunya, 2016-06-23)
Projecte Final de Màster Oficial
Accés obertIn this Master Thesis one of the most common problems related to face detection is presented: fast and accurate unconstrained face detection. To deal with this problem a new general learning method is presented. The proposed ... -
Perception for detection and grasping
(Springer, 2019)
Capítol de llibre
Accés obertThis research presents a methodology for the detection of the crawler used in the project AEROARMS. The approach consisted on using a two-step progressive strategy, going from rough detection and tracking, for approximation ... -
PhysXNet: a customizable approach for learning cloth dynamics on dressed people
(Institute of Electrical and Electronics Engineers (IEEE), 2021)
Text en actes de congrés
Accés obertWe introduce PhysXNet, a learning-based approach to predict the dynamics of deformable clothes given 3D skeleton motion sequences of humans wearing these clothes. The proposed model is adaptable to a large variety of ... -
PL-SLAM: real-time monocular visual SLAM with points and lines
(IEEE Press, 2017)
Text en actes de congrés
Accés obertLow textured scenes are well known to be one of the main Achilles heels of geometric computer vision algorithms relying on point correspondences, and in particular for visual SLAM. Yet, there are many environments in which, ... -
Relative localization for aerial manipulation with PL-SLAM
(Springer, 2019)
Capítol de llibre
Accés obertThis chapter explains a precise SLAM technique, PL-SLAM, that allows to simultaneously process points and lines and tackle situations where point-only based methods are prone to fail, like poorly textured scenes or motion ... -
Single-view 3d body and cloth reconstruction under complex poses
(Scitepress, 2022)
Text en actes de congrés
Accés obertRecent advances in 3D human shape reconstruction from single images have shown impressive results, leveraging on deep networks that model the so-called implicit function to learn the occupancy status of arbitrarily dense ... -
SMPLicit: Topology-aware generative model for clothed people
(Institute of Electrical and Electronics Engineers (IEEE), 2021)
Text en actes de congrés
Accés obertIn this paper we introduce SMPLicit, a novel generative model to jointly represent body pose, shape and clothing geometry. In contrast to existing learning-based approaches that require training specific models for each ...
