Recherche

Afficher tous les résultats pour

Accueil

Personne

Pascal Fua

À propos
Confidentialité
Mentions légales

Graph Chatbot

Publications associées (319)

Page 2 sur 16

Joint Pose Estimator and Feature Learning for Object Detection

Pascal Fua, François Fleuret, David Hasler, Karim Ali

A new learning strategy for object detection is presented. The proposed scheme forgoes the need to train a collection of detectors dedicated to homogeneous families of poses, and instead learns a single classifier that has the inherent ability to deform ba ...

Ieee Service Center, 445 Hoes Lane, Po Box 1331, Piscataway, Nj 08855-1331 Usa2009

Using Motion Cues to Supervise Single-Frame Body Pose and Shape Estimation in Low Data Regimes

Pascal Fua, Mathieu Salzmann, Andrey Davydov

When enough annotated training data is available, supervised deep-learning. algorithms excel at estimating human body pose and shape using a single camera. The effects of too little such data being available can be mitigated by using other information sour ...

Journal of Machine Learning Research Inc.2024

NeuroMorph: A Toolset for the Morphometric Analysis and Visualization of 3D Models Derived from Electron Microscopy Image Stacks

Pascal Fua, Graham Knott, Corrado Cali, Biagio Nigro, Anne Alison Jorstad

Serial electron microscopy imaging is crucial for exploring the structure of cells and tissues. The development of block face scanning electron microscopy methods and their ability to capture large image stacks, some with near isotropic voxels, is proving ...

Humana Press2015

Matching Seqlets: An Unsupervised Approach for Locality Preserving Sequence Matching

Pascal Fua, Xinchao Wang

In this paper, we propose a novel unsupervised approach for sequence matching by explicitly accounting for the locality properties in the sequences. In contrast to conventional approaches that rely on frame-to-frame matching, we conduct matching using sequ ...

2021

Persistent Homology with Improved Locality Information for more Effective Delineation

Pascal Fua, Kathryn Hess Bellwald, Mateusz Kozinski, Doruk Oner, Adélie Eliane Garin

Persistent Homology (PH) has been successfully used to train networks to detect curvilinear structures and to improve the topological quality of their results. However, existing methods are very global and ignore the location of topological features. In th ...

2022

A Generative Model for True Orthorectification

Pascal Fua, Christoph Strecha

Orthographic images compose an efficient and economic way to represent aerial images. This kind of information allows to measure two-dimensional objects and relate these to Geographic Information Systems. This paper deals with the computation of a true ort ...

2008

Generating LOD3 building models from structure-from-motion and semantic segmentation

Pascal Fua, Katrin Beyer, Radhakrishna Achanta, Fernando Perez Cruz, Bryan German Pantoja Rosero, Mateusz Kozinski

This paper describes a pipeline for automatically generating level of detail (LOD) models (digital twins), specifically LOD2 and LOD3, from free-standing buildings. Our approach combines structure from motion (SfM) with deep-learning-based segmentation tec ...

2022

Temporally-Consistent Surface Reconstruction Using Metrically-Consistent Atlases

Pascal Fua, Mathieu Salzmann, Shaifali Parashar, Jan Bednarík

We propose a method for unsupervised reconstruction of a temporally-consistent sequence of surfaces from a sequence of time-evolving point clouds. It yields dense and semantically meaningful correspondences between frames. We represent the reconstructed su ...

2025

Dendritic tree extraction from noisy maximum intensity projection images in C-elegans

Pascal Fua, Raphael Sznitman

Background: Maximum Intensity Projections (MIP) of neuronal dendritic trees obtained from confocal microscopy are frequently used to study the relationship between tree morphology and mechanosensory function in the model organism C. elegans. Extracting den ...

Biomed Central Ltd2014

Automated Parameterization for Aerodynamic Shape Optimization via Deep Geometric Learning

Pascal Fua, Zhen Wei

Traditional aerodynamic shape optimization (ASO) is costly and time-intensive, requiring extensive manual tuning for parameterization to define the design space and manipulate geometries. Conventional parameterization methods limit flexibility and demand s ...

American Institute of Aeronautics and Astronautics (AIAA)2025

Vision-Based Unmanned Aerial Vehicle Detection and Tracking for Sense and Avoid Systems

Krishna Raj Sapkota, Pascal Fua, Denis Gillet, Alcherio Martinoli, Vincent Lepetit, Steven Adriaan Roelofsen, Artem Rozantsev

We propose an approach for on-line detection of small Unmanned Aerial Vehicles (UAVs) and estimation of their relative positions and velocities in the 3D environment from a single moving camera in the context of sense and avoid systems. This problem is cha ...

Ieee2016

Introducing Geometry in Active Learning for Image Segmentation

Pascal Fua, Raphael Sznitman, Ksenia Konyushkova

We propose an Active Learning approach to training a segmentation classifier that exploits geometric priors to streamline the annotation process in 3D image volumes. To this end, we use these priors not only to select voxels most in need of annotation but ...

2015

Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures

Pascal Fua

Real-time free-view human rendering from sparse-view RGB inputs is a challenging task due to the sensor scarcity and the tight time budget. To ensure efficiency, recent methods leverage 2D CNNs operating in texture space to learn rendering primitives. Howe ...

IEEE2025

Unsupervised Geometry-Aware Representation Learning for 3D Human Pose Estimation

Pascal Fua, Mathieu Salzmann, Helge Jochen Rhodin

Modern 3D human pose estimation techniques rely on deep networks, which require large amounts of training data. While weakly-supervised methods require less supervision, by utilizing 2D poses or multi-view imagery without annotations, they still need a suf ...

2018

Enabling Uncertainty Estimation in Iterative Neural Networks

Pascal Fua, Minh Hieu Lê, Doruk Oner, Nikita Durasov

Turning pass-through network architectures into iterative ones, which use their own output as input, is a well-known approach for boosting performance. In this paper, we argue that such architectures offer an additional benefit: The convergence rate of the ...

Curran Associates2024

Harnessing deep learning to detect bronchiolitis obliterans syndrome from chest CT

Pascal Fua, Michele De Palma, Nahal Mansouri, Jakub Jan Gwizdala

BackgroundBronchiolitis Obliterans Syndrome (BOS), a fibrotic airway disease that may develop after lung transplantation, conventionally relies on pulmonary function tests (PFTs) for diagnosis due to limitations of CT imaging. Deep neural networks (DNNs) h ...

SPRINGERNATURE2025

Learning to Reconstruct Texture-less Deformable Surfaces from a Single View

Pascal Fua, Mathieu Salzmann, Jan Bednarík

Recent years have seen the development of mature solutions for reconstructing deformable surfaces from a single image, provided that they are relatively well-textured. By contrast, recovering the 3D shape of texture-less surfaces remains an open problem, a ...

2018

Leveraging Spatial and Photometric Context for Calibrated Non-Lambertian Photometric Stereo

Pascal Fua, Engin Türetken, David Honzátko

The problem of estimating a surface shape from its observed reflectance properties still remains a challenging task in computer vision. The presence of global illumination effects such as inter-reflections or cast shadows makes the task particularly diffic ...

IEEE COMPUTER SOC2021

Visual Correspondences for Unsupervised Domain Adaptation on Electron Microscopy Images

Pascal Fua, Mathieu Salzmann, Carlos Joaquin Becker, Róger Bermúdez Chacón, Okan Altingövde

We present an Unsupervised Domain Adaptation strategy to compensate for domain shifts on Electron Microscopy volumes. Our method aggregates visual correspondences—motifs that are visually similar across different acquisitions—to infer changes on the parame ...

Institute of Electrical and Electronics Engineers2020

Supervoxel-Based Segmentation of Mitochondria in EM Image Stacks with Learned Shape Features

Pascal Fua, Graham Knott, Radhakrishna Achanta, Kevin Smith, Aurélien Lucchi

It is becoming increasingly clear that mitochondria play an important role in neural function. Recent studies show mitochondrial morphology to be crucial to cellular physiology and synaptic function and a link between mitochondrial defects and neuro-degene ...

Institute of Electrical and Electronics Engineers2012