Home

Person

Pascal Fua

About
Privacy
Disclaimer

Graph Chatbot

Related publications (319)

Page 4 of 16

Systems and methods for tracking interacting objects

Pascal Fua, François Fleuret, Engin Türetken, Xinchao Wang

Systems and methods for tracking interacting objects may acquire, with a sensor, and two or more images associated with two or more time instances. A processor may generate image data from the two or more images. The processor may apply an extended Probabi ...

2015

Residual Parameter Transfer for Deep Domain Adaptation

Pascal Fua, Mathieu Salzmann, Artem Rozantsev

The goal of Deep Domain Adaptation is to make it possible to use Deep Nets trained in one domain where there is enough annotated training data in another where there is little or none. Most current approaches have focused on learning feature representation ...

2018

Sketch2Mesh: Reconstructing and Editing 3D Shapes from Sketches

Pascal Fua, Benoît Alain René Guillard, Edoardo Remelli, Pierre Mathieu Yvernay

Reconstructing 3D shape from 2D sketches has long been an open problem because the sketches only provide very sparse and ambiguous information. In this paper, we use an encoder/decoder architecture for the sketch to mesh translation. When integrated into a ...

IEEE2021

GECCO: Geometrically-Conditioned Point Diffusion Models

Pascal Fua, Eduard Trulls Fortuny, Michal Jan Tyszkiewicz

Diffusion models generating images conditionally on text, such as Dall-E 2 [51] and Stable Diffusion[53], have recently made a splash far beyond the computer vision community. Here, we tackle the related problem of generating point clouds, both uncondition ...

Ieee Computer Soc2023

Robust Non-Rigid Registration of 2D and 3D Graphs

Pascal Fua, Przemyslaw Rafal Glowacki, Jan Kybic

We present a new approach to matching graphs embedded in R2 or R3. Unlike earlier methods, our approach does not rely on the similarity of local appearance features, does not require an initial alignment, can handle partial matches, and can cope with non-l ...

2012

Shape optimisation of technical devices via gradient descent using convolutional neural network proxies

Pascal Fua, François Fleuret, Pierre Bruno Baqué

The present invention generally relates to a method, a system and a computer program for shape optimisation of a technical device adapted to be exposed to a fluid flowing around a contour of said device with respect to its fluid dynamic parameters. In orde ...

2019

Learning Context Cues for Synapse Segmentation

Pascal Fua, Graham Knott, Carlos Joaquin Becker, Karim Ali

We present a new approach for the automated segmentation of synapses in image stacks acquired by Electron Microscopy (EM) that relies on image features specifically designed to take spatial context into account. These features are used to train a classifie ...

Institute of Electrical and Electronics Engineers2013

Voxel2Mesh: 3D Mesh Model Generation from Volumetric Data

Pascal Fua, Graham Knott, Edoardo Remelli, Pamuditha Udaranga Wickramasinghe

CNN-based volumetric methods that label individual voxels now dominate the field of biomedical segmentation. However, 3D surface representations are often required for proper analysis. They can be obtained by post-processing the labeled volumes which typic ...

2020

Domain Adaptation for Microscopy Imaging

Pascal Fua, Carlos Joaquin Becker, Christos Marios Christoudias

Electron and Light Microscopy imaging can now deliver high-quality image stacks of neural structures. However, the amount of human annotation effort required to analyze them remains a major bottleneck. While Machine Learning algorithms can be used to help ...

Institute of Electrical and Electronics Engineers2015

Feature Harvesting for Tracking-by-Detection

Pascal Fua, François Fleuret, Vincent Lepetit, Mustafa Özuysal

We propose a fast approach to 3D object detection and pose estimation that owes its robustness to a training phase during which the target object slowly moves with respect to the camera. No additional information is provided to the system, save a very roug ...

Springer2006

Correlative In Vivo 2-Photon Beam Scanning Electron Microscopy: 3D Analysis of Neuronal Ultrastructure

Pascal Fua, Graham Knott, Anne Alison Jorstad, Bohumil Maco

This protocol describes how dendrites and axons, imaged in vivo, can subsequently be analyzed in 3D using focused ion beam scanning electron microscopy (FIBSEM). The fluorescent structures are identified after chemical fixation and their position highlight ...

Elsevier Academic Press Inc2014

Implicit Meshes for Effective Silhouette Handling

Pascal Fua, Mathieu Salzmann, Slobodan Ilic

Using silhouettes in uncontrolled environments typically requires handling occlusions as well as changing or cluttered backgrounds, which limits the applicability of most silhouette based methods. For the purpose of 3--D shape modeling, we show that repres ...

Springer Verlag2007

A method and system for enforcing smoothness constraints on surface meshes from a graph convolutional neural network

Pascal Fua, Pamuditha Udaranga Wickramasinghe

A method for enforcing smoothness constraints on surface meshes produced by a Graph Convolutional Neural Network (GCNN) including the steps of reading image data from a memory, the image data including two-dimensional image data representing a three-dimens ...

2023

Deep Active Surface Models

Pascal Fua, Graham Knott, Pamuditha Udaranga Wickramasinghe

Active Surface Models have a long history of being useful to model complex 3D surfaces. But only Active Contours have been used in conjunction with deep networks, and then only to produce the data term as well as meta-parameter maps controlling them. In th ...

2021

Multiple Object Tracking using K-Shortest Paths Optimization

Pascal Fua, François Fleuret, Engin Türetken

Multi-object tracking can be achieved by detecting objects in individual frames and then linking detections across frames. Such an approach can be made very robust to the occasional detection failure: If an object is not detected in a frame but is in previ ...

Institute of Electrical and Electronics Engineers2011

A Domain-Adaptive Two-Stream U-Net For Electron Microscopy Image Segmentation

Pascal Fua, Mathieu Salzmann, Pablo Marquez Neila

Deep networks such as the U-Net are outstanding at segmenting biomedical images when enough training data is available, but only then. Here we introduce a Domain Adaptation approach that relies on two coupled U-Nets that either regularize or share correspo ...

IEEE2018

Enforcing Connectivity of 3D Linear Structures Using Their 2D Projections

Pascal Fua, Mateusz Kozinski, Doruk Oner, Hussein Fadl Hassan Hassan Osman

Many biological and medical tasks require the delineation of 3D curvilinear structures such as blood vessels and neurites from image volumes. This is typically done using neural networks trained by minimizing voxel-wise loss functions that do not capture t ...

SPRINGER INTERNATIONAL PUBLISHING AG2022

Estimation and visualization of sagittal kinematics of lower limbs orientation using body-fixed sensors

Kamiar Aminian, Pascal Fua, Hooman Dejnabadi, Emilio Casanova

A new method of estimating lower limbs orientations using a combination of accelerometers and gyroscopes is presented. The model is based on estimating the accelerations of ankle and knee joints by placing virtual sensors at the centers of rotation. The pr ...

Institute of Electrical and Electronics Engineers2006

A Domain-Adaptive Two-Stream U-Net for Electron Microscopy Image Segmentation

Pascal Fua, Mathieu Salzmann, Pablo Marquez Neila, Róger Bermúdez Chacón

2018

Latent Representation of CFD Meshes and Application to Airfoil Aerodynamics

Pascal Fua, Benoît Alain René Guillard, Zhen Wei

Mesh manipulation is central to Computational Fluid Dynamics (CFD). 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 p ...

American Institute of Aeronautics and Astronautics2023