Home

Person

Pascal Fua

About
Privacy
Disclaimer

Graph Chatbot

Related publications (319)

Page 13 of 16

Direct Prediction of 3D Body Poses from Motion Compensated Sequences

Pascal Fua, Vincent Lepetit, Artem Rozantsev, Bugra Tekin

We propose an efficient approach to exploiting motion information from consecutive frames of a video sequence to recover the 3D pose of people. Previous approaches typically compute candidate poses in individual frames and then link them in a post-processi ...

2016

An Optimal Policy for Target Localization with Application to Electron Microscopy

Pascal Fua, Raphael Sznitman, Aurélien Lucchi

This paper considers the task of finding a target location by making a limited number of sequential observations. Each observation results from evaluating an imperfect classifier of a chosen cost and accuracy on an interval of chosen length and position. W ...

2013

Tracklet-based Multi-Commodity Network Flow for Tracking Multiple People

François Fleuret, Pascal Fua, Horesh Beny Ben Shitrit

(EN)A method for continuously tracking multiple people partitioned into groups while preserving identities under global appearance constraints, wherein people's trajectories may intersect, and wherein only sparse appearance information is available is disc ...

WO2013

Real-Time Non-Rigid Surface Detection

Pascal Fua, Vincent Lepetit, Julien Pilet

We present a real-time method for detecting deformable surfaces, with no need whatsoever for a priori pose knowledge. Our method starts from a set of wide baseline point matches between an undeformed image of the object and the image in which it is to be d ...

2005

Pose Priors for Simultaneously Solving Alignment and Correspondence

Pascal Fua, Vincent Lepetit

Estimating a camera pose given a set of 3D-object and 2D-image feature points is a well understood problem when correspondences are given. However, when such correspondences cannot be established a priori, one must simultaneously compute them along with th ...

Springer2008

Large occlusion completion using normal maps

Pascal Fua, Christoph Strecha, Engin Tola

Dense disparity maps can be computed from wide-baseline stereo pairs but will inevitably contain large areas where the depth cannot be estimated accurately because the pixels are seen in one view only. A traditional approach to this problem is to introduce ...

2010

Image Summaries using Database Saliency

Pascal Fua, Sabine Süsstrunk, Radhakrishna Achanta, Appu Shaji

It is useful to have a small set of representative images from a database of thousands of images to summarize its content. There are two key aspects of such image summaries: how to generate them and how to present them. We address both issues. We extend th ...

2009

Gradient Response Maps for Real-Time Detection of Textureless Objects

Pascal Fua, Vincent Lepetit, Slobodan Ilic

We present a method for real-time 3D object instance detection that does not require a time-consuming training stage, and can handle untextured objects. At its core, our approach is a novel image representation for template matching designed to be robust t ...

Institute of Electrical and Electronics Engineers2012

3D pose refinement from reflections

Pascal Fua, Mathieu Salzmann, Vincent Lepetit

We demonstrate how to exploit reflections for accurate registration of shiny objects: The lighting environment can be retrieved from the reflections under a distant illumination assumption. Since it remains unchanged when the camera or the object of intere ...

Ieee Service Center, 445 Hoes Lane, Po Box 1331, Piscataway, Nj 08855-1331 Usa2008

What Players do with the Ball: A Physically Constrained Interaction Modeling

Pascal Fua, Xinchao Wang, Andrii Maksai

Tracking the ball is critical for video-based analysis of team sports. However, it is difficult, especially in low resolution images, due to the small size of the ball, its speed that creates motion blur, and its often being occluded by players. In this pa ...

2016

Active Learning and Proofreading for Delineation of Curvilinear Structures

Pascal Fua, Jakub Tarnawski, Agata Justyna Mosinska

Many state-of-the-art delineation methods rely on supervised machine learning algorithms. As a result, they require manually annotated training data, which is tedious to obtain. Furthermore, even minor classification errors may significantly affect the top ...

2017

Capturing 3D Stretchable Surfaces from Single Images in Closed Form

Pascal Fua, Mathieu Salzmann, Vincent Lepetit

We present a closed-form solution to the problem of re- covering the 3D shape of a non-rigid potentially stretchable surface from 3D-to-2D correspondences. In other words, we can reconstruct a surface from a single image without a priori knowledge of its d ...

2009

Long Term Motion Prediction Using Keyposes

Pascal Fua, Mathieu Salzmann, Wei Wang, Sena Kiciroglu

Long term human motion prediction is essential in safety-critical applications such as human-robot interaction and autonomous driving. In this paper we show that to achieve long term forecasting, predicting human pose at every time instant is unnecessary. ...

IEEE2022

Segmentation-driven 6D Object Pose Estimation

Pascal Fua, Mathieu Salzmann, Yinlin Hu, Joachim Ludovic Hugonot

The most recent trend in estimating the 6D pose of rigid objects has been to train deep networks to either directly regress the pose from the image or to predict the 2D locations of 3D keypoints, from which the pose can be obtained using a PnP algorithm. I ...

IEEE2019

A novel immersive catheter ablation simulator based on individualized 3D MR patients' heart models improves ablation performance of future electrophysiologists

Pascal Fua

Oxford University Press (OUP)2025

Latent Representation of Computational Fluid Dynamics Meshes and Application to Airfoil Aerodynamics

Pascal Fua, Benoît Alain René Guillard, Zhen Wei

Mesh manipulation is central to computational fluid dynamics. However, creating appropriate computational meshes often involves substantial manual intervention that has to be repeated each time the target shape changes. To address this problem, we propose ...

AMER INST AERONAUTICS ASTRONAUTICS2023

Simultaneous Pose, Correspondence and Non-Rigid Shape

Pascal Fua, Jonas Olof Martin Östlund

Recent works have shown that 3D shape of non-rigid surfaces can be accurately retrieved from a single im- age given a set of 3D-to-2D correspondences between that image and another one for which the shape is known. However, existing approaches assume that ...

2010

Eliminating Exposure Bias and Metric Mismatch in Multiple Object Tracking

Pascal Fua, Andrii Maksai

Identity Switching remains one of the main difficulties Multiple Object Tracking (MOT) algorithms have to deal with. Many state-of-the-art approaches now use sequence models to solve this problem but their training can be affected by biases that decrease t ...

IEEE2019

Daisy: An Efficient Dense Descriptor Applied to Wide Baseline Stereo

Pascal Fua, Vincent Lepetit, Engin Tola

In this paper, we introduce a local image descriptor, DAISY, which is very efficient to compute densely. We also present an EM based algorithm to compute dense depth and occlusion maps from wide baseline image pairs using this descriptor. This yields much ...

Institute of Electrical and Electronics Engineers2010

MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networks

Pascal Fua, Benoît Alain René Guillard, Federico Stella

Unsigned Distance Fields (UDFs) can be used to represent non-watertight surfaces. However, current approaches to converting them into explicit meshes tend to either be expensive or to degrade the accuracy. Here, we extend the marching cube algorithm to han ...

Springer2022