Exploració per autor "Moreno-Noguer, Francesc"
Ara es mostren els items 64-83 de 157
-
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 ... -
Generating attribution maps with disentangled masked backpropagation
(Institute of Electrical and Electronics Engineers (IEEE), 2021)
Text en actes de congrés
Accés obertAttribution map visualization has arisen as one of the most effective techniques to understand the underlying inference process of Convolutional Neural Networks. In this task, the goal is to compute an score for each image ... -
Geodesic finite mixture models
(2014)
Text en actes de congrés
Accés obertWe present a novel approach for learning a finite mixture model on a Riemannian manifold in which Euclidean metrics are not applicable and one needs to resort to geodesic distances consistent with the manifold geometry. ... -
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 ... -
Global model with local interpretation for dynamic shape reconstruction
(2017)
Text en actes de congrés
Accés obertThe most standard approach to resolve the inherent ambiguities of the non-rigid structure from motion problem is using low-rank models that approximate deforming shapes by a linear combination of rigid basis. These models ... -
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 ... -
Hallucinating dense optical flow from sparse lidar for autonomous vehicles
(Institute of Electrical and Electronics Engineers (IEEE), 2018)
Text en actes de congrés
Accés obertIn this paper we propose a novel approach to estimate dense optical flow from sparse lidar data acquired on an autonomous vehicle. This is intended to be used as a drop-in replacement of any image-based optical flow system ... -
Human motion prediction via spatio-temporal inpainting
(Institute of Electrical and Electronics Engineers (IEEE), 2019)
Text en actes de congrés
Accés obertWe propose a Generative Adversarial Network (GAN) to forecast 3D human motion given a sequence of past 3D skeleton poses. While recent GANs have shown promising results, they can only forecast plausible motion over relatively ... -
Image collection pop-up: 3D reconstruction and clustering of rigid and non-rigid categories
(Institute of Electrical and Electronics Engineers (IEEE), 2018)
Text en actes de congrés
Accés obertThis paper introduces an approach to simultaneously estimate 3D shape, camera pose, and object and type of deformation clustering, from partial 2D annotations in a multi-instance collection of images. Furthermore, we can ... -
Improving map re-localization with deep 'movable' objects segmentation on 3D LiDAR point clouds
(2019)
Text en actes de congrés
Accés obertLocalization and Mapping is an essential compo-nent to enable Autonomous Vehicles navigation, and requiresan accuracy exceeding that of commercial GPS-based systems.Current odometry and mapping algorithms are able to ... -
Integrating human body mocaps into Blender using RGB images
(International Academy, Research, and Industry Association (IARIA), 2020)
Text en actes de congrés
Accés obertReducing the complexity and cost of a Motion Capture (MoCap) system has been of great interest in recent years. Unlike other systems that use depth range cameras, we present an algorithm that is capable of working as a ... -
Integration of deformable contours and a multiple hypotheses Fisher color model for robust tracking in varying illuminant environments
(Elsevier BV, 2007)
Article
Accés obertIn this paper we propose a new technique to perform figure-ground segmentation in image sequences of moving objects under varying illumination conditions. Unlike most of the algorithms that adapt color, there is not the ... -
Interactive multiple object learning with scanty human supervision
(2016-08)
Article
Accés obertWe present a fast and online human-robot interaction approach that progressively learns multiple object classifiers using scanty human supervision. Given an input video stream recorded during the human robot interaction, ... -
Joint coarse-and-fine reasoning for deep optical flow
(Institute of Electrical and Electronics Engineers (IEEE), 2017)
Text en actes de congrés
Accés obertWe propose a novel representation for dense pixel-wise estimation tasks using CNNs that boosts accuracy and reduces training time, by explicitly exploiting joint coarse-and-fine reasoning. The coarse reasoning is performed ... -
Learned vertex descent: a new direction for 3D human model fitting
(Springer, 2022)
Text en actes de congrés
Accés obertWe propose a novel optimization-based paradigm for 3D human model fitting on images and scans. In contrast to existing approaches that directly regress the parameters of a low-dimensional statistical body model (e.g. SMPL) ... -
Learning depth-aware deep representations for robotic perception
(Institute of Electrical and Electronics Engineers (IEEE), 2017)
Article
Accés obertExploiting RGB-D data by means of Convolutional Neural Networks (CNNs) is at the core of a number of robotics applications, including object detection, scene semantic segmentation and grasping. Most existing approaches, ... -
Learning RGB-D descriptors of garment parts for informed robot grasping
(2014)
Article
Accés obertRobotic handling of textile objects in household environments is an emerging application that has recently received considerable attention thanks to the development of domestic robots. Most current approaches follow a ... -
Learning shape, motion and elastic models in force space
(Institute of Electrical and Electronics Engineers (IEEE), 2015)
Text en actes de congrés
Accés obertIn this paper, we address the problem of simultaneously recovering the 3D shape and pose of a deformable and potentially elastic object from 2D motion. This is a highly ambiguous problem typically tackled by using low-rank ...
