Publications by Pascal Fua | EPFL Graph Search

Related publications (319)

Eigendecomposition-Free Training of Deep Networks for Linear Least-Square Problems

Pascal Fua, Mathieu Salzmann, Kwang Moo Yi, Yinlin Hu, Zheng Dang

Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be tackled by solving a linear least-square problem, which can be done by finding the eigenvector corresponding to the smal ...

IEEE COMPUTER SOC2021

Learning for Structured Prediction Using Approximate Subgradient Descent with Working Sets

Pascal Fua, Aurélien Lucchi, Yunpeng Li

We propose a working set based approximate subgradient descent algorithm to minimize the margin-sensitive hinge loss arising from the soft constraints in max-margin learning frameworks, such as the structured SVM. We focus on the setting of general graphic ...

2013

BigNeuron: a resource to benchmark and predict performance of algorithms for automated tracing of neurons in light microscopy datasets

Pascal Fua, Sean Lewis Hill, Jiancheng Yang, Amos Sironi, Jian Yang

BigNeuron is an open community bench-testing platform with the goal of setting open standards for accurate and fast automatic neuron tracing. We gathered a diverse set of image volumes across several species that is representative of the data obtained in m ...

Nature Publishing Group2023

Overcoming the Domain Gap in Neural Action Representations

Pascal Fua, Pavan P Ramdya, Semih Günel, Sina Honari, Florian Aymanns

Relating behavior to brain activity in animals is a fundamental goal in neuroscience, with practical applications in building robust brain-machine interfaces. However, the domain gap between individuals is a major issue that prevents the training of genera ...

SPRINGER2022

Joint Segmentation and Path Classification of Curvilinear Structures

Pascal Fua, Mateusz Kozinski, Agata Justyna Mosinska

Detection of curvilinear structures in images has long been of interest. One of the most challenging aspects of this problem is inferring the graph representation of the curvilinear network. Most existing delineation approaches first perform binary segment ...

2020

Automatic Parameterization for Aerodynamic Shape Optimization via Deep Geometric Learning

Pascal Fua, Zhen Wei

We propose two deep learning models that fully automate shape parameterization for aerodynamic shape optimization. Both models are optimized to parameterize via deep geometric learning to embed human prior knowledge into learned geometric patterns, elimina ...

2023

GarNet++: Improving Fast and Accurate Static 3D Cloth Draping by Curvature Loss

Pascal Fua, Mathieu Salzmann, Shaifali Parashar, Victor Constantin, Erhan Gündogdu

In this paper, we tackle the problem of static 3D cloth draping on virtual human bodies. We introduce a two-stream deep network model that produces a visually plausible draping of a template cloth on virtual 3D bodies by extracting features from both the b ...

2022

XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera

Pascal Fua, Helge Jochen Rhodin

We present a real-time approach for multi-person 3D motion capture at over 30 fps using a single RGB camera. It operates successfully in generic scenes which may contain occlusions by objects and by other people. Our method operates in subsequent stages. T ...

2020

What Face and Body Shapes Can Tell Us About Height

Pascal Fua, Helge Jochen Rhodin, Semih Günel

Recovering a person's height from a single image is important for virtual garment fitting, autonomous driving and surveillance. However, it is also very challenging without absolute scale information. Here, we examine the rarely addressed case, where camer ...

IEEE COMPUTER SOC2019

Learning to Segment 3D Linear Structures Using Only 2D Annotations

Pascal Fua, Mathieu Salzmann, Mateusz Kozinski, Agata Justyna Mosinska

We propose a loss function for training a Deep Neural Network (DNN) to segment volumetric data, that accommodates ground truth annotations of 2D projections of the training volumes, instead of annotations of the 3D volumes themselves. In consequence, we si ...

SPRINGER INTERNATIONAL PUBLISHING AG2018

Linear Local Models for Monocular Reconstruction of Deformable Surfaces

Pascal Fua, Mathieu Salzmann

Recovering the 3D shape of a nonrigid surface from a single viewpoint is known to be both ambiguous and challenging. Resolving the ambiguities typically requires prior knowledge about the most likely deformations that the surface may undergo. It often take ...

2011

Thick Boundaries in Binary Space and Their Influence on Nearest-Neighbor Search

Pascal Fua, Vincent Lepetit, Tomasz Piotr Trzcinski

Binary descriptors allow faster similarity computation than real-valued ones while requiring much less storage. As a result, many algorithms have recently been proposed to binarize ﬂoating-point descriptors so that they can be searched for quickly. Unfortu ...

Elsevier2012

State of the Art in Dense Monocular Non-Rigid 3D Reconstruction

Pascal Fua

3D reconstruction of deformable (or non-rigid) scenes from a set of monocular 2D image observations is a long-standing and actively researched area of computer vision and graphics. It is an ill-posed inverse problem, since-without additional prior assumpti ...

WILEY2023

Counting People by Estimating People Flows

Pascal Fua, Mathieu Salzmann, Weizhe Liu

Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in video sequences, and those that do only impose weak smoothness co ...

2022

Projection onto the Manifold of Elongated Structures for Accurate Extraction

Pascal Fua, Vincent Lepetit, Amos Sironi

Detection of elongated structures in 2D images and 3D image stacks is a critical prerequisite in many applications and Machine Learning-based approaches have recently been shown to deliver superior performance. However, these methods essentially classify i ...

2015

Perspective Aware Road Obstacle Detection

Pascal Fua, Mathieu Salzmann, Sina Honari, Krzysztof Maciej Lis

While road obstacle detection techniques have become increasingly effective, they typically ignore the fact that, in practice, the apparent size of the obstacles decreases as their distance to the vehicle increases. In this letter, we account for this by c ...

2023

3D reconstruction of curvilinear structures with stereo matching deep convolutional neural networks

Pascal Fua, Cécile Hébert, Emad Oveisi, Anastasiia Mishchuk, Okan Altingövde, Gulnaz Ganeeva

Curvilinear structures frequently appear in microscopy imaging as the object of interest. Crystallographic defects, i.e dislocations, are one of the curvilinear structures that have been repeatedly investigated under transmission electron microscopy (TEM) ...

ELSEVIER2022

Defect segmentation for multi-illumination quality control systems

Pascal Fua, Engin Türetken, Siavash Arjomand Bigdeli, David Honzátko

Thanks to recent advancements in image processing and deep learning techniques, visual surface inspection in production lines has become an automated process as long as all the defects are visible in a single or a few images. However, it is often necessary ...

2021

Non-Linear Domain Adaptation with Boosting

Pascal Fua, Carlos Joaquin Becker, Christos Marios Christoudias

A common assumption in machine vision is that the training and test samples are drawn from the same distribution. However, there are many problems when this assumption is grossly violated, as in bio-medical applications where different acquisitions can gen ...

2013

Geometry in active learning for binary and multi-class image segmentation

Pascal Fua, Raphael Sznitman, Ksenia Konyushkova

We propose an active learning approach to image segmentation that exploits geometric priors to speed up and streamline the annotation process. It can be applied for both background foreground and multi-class segmentation tasks in 2D images and 3D image vol ...

2019