Home

Person

Pascal Fua

About
Privacy
Disclaimer

Graph Chatbot

Related publications (319)

Page 14 of 16

Vision-based power line cables and pylons detection for low flying aircraft

Pascal Fua, Jakub Jan Gwizdala, Soumava Kumar Roy, Mian Akbar Shah

Power lines are dangerous for low-flying aircraft, especially in low-visibility conditions. Thus, a vision-based system able to analyze the aircraft's surroundings and to provide the pilots with a "second pair of eyes" can contribute to enhancing their saf ...

SPRINGER2025

Probabilistic Atlases to Enforce Topological Constraints

Pascal Fua, Graham Knott, Pamuditha Udaranga Wickramasinghe

Probabilistic atlases (PAs) have long been used in standard segmentation approaches and, more recently, in conjunction with Convolutional Neural Networks (CNNs). However, their use has been restricted to relatively standardized structures such as the brain ...

2019

Retrieving multiple light sources in the presence of specular reflections and texture

Pascal Fua

Recovering multiple point light sources from a sparse set of photographs in which objects of unknown texture can move is challenging. This is because both diffuse and specular reflections appear to slide across surfaces, which is a well known physical fact ...

Elsevier2008

On Benchmarking Camera Calibration and Multi-View Stereo for High Resolution Imagery

Pascal Fua, Christoph Strecha

In this paper we want to start the discussion on whether image based 3-D modelling techniques can possibly be used to replace LIDAR systems for outdoor 3D data acquisition. Two main issues have to be addressed in this context: (i) camera calibration (inter ...

2008

Template-based Monocular 3D Shape Recovery using Laplacian Meshes

Pascal Fua, Tien Dat Ngo, Jonas Olof Martin Östlund

We show that by extending the Laplacian formalism, which was first introduced in the Graphics community to regularize 3D meshes, we can turn the monocular 3D shape reconstruction of a deformable surface given correspondences with a reference image into a w ...

Institute of Electrical and Electronics Engineers2016

On Rendering Synthetic Images for Training an Object Detector

Pascal Fua, Vincent Lepetit, Artem Rozantsev

We propose a novel approach to synthesizing images that are effective for training object detectors. Starting from a small set of real images, our algorithm estimates the rendering parameters required to synthesize similar images given a coarse 3D model of ...

Elsevier2015

Laplacian Meshes for Monocular 3D Shape Recovery

Pascal Fua, Aydin Varol, Tien Dat Ngo, Jonas Olof Martin Östlund

2012

Structured Image Segmentation using Kernelized Features

Pascal Fua, Kevin Smith, Aurélien Lucchi, Yunpeng Li

Most state-of-the-art approaches to image segmentation formulate the problem using Conditional Random Fields. These models typically include a unary term and a pairwise term, whose parameters must be carefully chosen for optimal performance. Recently, stru ...

2012

Mo(2)Cap(2): Real-time Mobile 3D Motion Capture with a Cap-mounted Fisheye Camera

Pascal Fua, Helge Jochen Rhodin

We propose the first real-time system for the egocentric estimation of 3D human body pose in a wide range of unconstrained everyday activities. This setting has a unique set of challenges, such as mobility of the hardware setup, and robustness to long capt ...

2019

Adversarial Parametric Pose Prior

Andrey Davydov, Pascal Fua, Mathieu Salzmann, Victor Constantin, Sina Honari, Anastasia Remizova

The Skinned Multi-Person Linear (SMPL) model represents human bodies by mapping pose and shape parameters to body meshes. However, not all pose and shape parameter values yield physically-plausible or even realistic body meshes. In other words, SMPL is und ...

IEEE2022

BRIEF: Computing a Local Binary Descriptor Very Fast

Pascal Fua, Vincent Lepetit, Christoph Strecha, Michael Calonder, Tomasz Piotr Trzcinski, Mustafa Özuysal

Binary descriptors are becoming increasingly popular as a means to compare feature points very fast and while requiring comparatively small amounts of memory. The typical approach to creating them is to first compute floating-point ones, using an algorithm ...

Institute of Electrical and Electronics Engineers2012

Robust People Tracking with Global Trajectory Optimization

Pascal Fua, François Fleuret

Given three or four synchronized videos taken at eye level and from different angles, we show that we can effectively use dynamic programming to accurately follow up to six individuals across thousands of frames in spite of significant occlusions. In addit ...

2006

Method and apparatus for multiple object tracking with k-shortest paths

Pascal Fua, François Fleuret

Trajectories of objects are estimated by determining the optimal solution(s) of a tracking model on the basis of an occupancy probability distribution. The occupancy probability distribution is the probability of presence of objects over a set of discrete ...

2013

Tracking Interacting Objects Using Intertwined Flows

Pascal Fua, François Fleuret, Engin Türetken, Xinchao Wang

In this paper, we show that tracking different kinds of interacting objects can be formulated as a network-flow Mixed Integer Program. This is made possible by tracking all objects simultaneously using intertwined flow variables and expressing the fact tha ...

Institute of Electrical and Electronics Engineers2016

UCLID-Net: Single View Reconstruction in Object Space

Pascal Fua, Benoît Alain René Guillard, Edoardo Remelli

Most state-of-the-art deep geometric learning single-view reconstruction approaches rely on encoder-decoder architectures that output either shape parametrizations or implicit representations. However, these representations rarely preserve the Euclidean st ...

2020

An Investigation of Model Bias in 3D Face Tracking

Pascal Fua, Vincent Lepetit

2005

Domain-Adaptive Multibranch Networks

Pascal Fua, Mathieu Salzmann, Róger Bermúdez Chacón

We tackle unsupervised domain adaptation by accounting for the fact that different domains may need to be processed differently to arrive to a common feature representation effective for recognition. To this end, we introduce a deep learning framework wher ...

2020

Deep Active Latent Surfaces for Medical Geometries

Pascal Fua

Shape priors have long been known to be effective when reconstructing 3D shapes from noisy or incomplete data. When using a deep-learning based shape representation, this often involves learning a latent representation, which can be either in the form of a ...

2025

Simultaneous Point Matching and 3D Deformable Surface Reconstruction

Pascal Fua, Appu Shaji, Aydin Varol

It has been shown that the 3D shape of a deformable surface in an image can be recovered by establishing correspondences between that image and a reference one in which the shape is known. These matches can then be used to set-up a convex optimization prob ...

Ieee Computer Soc Press, Customer Service Center, Po Box 3014, 10662 Los Vaqueros Circle, Los Alamitos, Ca 90720-1264 Usa2010

Linking Pose and Motion

Pascal Fua

Algorithms designed to estimate 3D pose in video sequences enforce temporal consistency but typically overlook an important source of information: The 3D pose of an object, be it rigid or articulated, has a direct influence on its direction of travel. In t ...

2008