Home

Person

Pascal Fua

About
Privacy
Disclaimer

Graph Chatbot

Related publications (319)

Page 10 of 16

Neural Scene Decomposition for Multi-Person Motion Capture

Pascal Fua, Mathieu Salzmann, Helge Jochen Rhodin, Isinsu Katircioglu, Victor Constantin

Learning general image representations has proven key to the success of many computer vision tasks. For example, many approaches to image understanding problems rely on deep networks that were initially trained on ImageNet, mostly because the learned featu ...

IEEE2019

Multiscale Centerline Detection by Learning a Scale-Space Distance Transform

Pascal Fua, Vincent Lepetit, Amos Sironi

We propose a robust and accurate method to extract the centerlines and scale of tubular structures in 2D images and 3D volumes. Existing techniques rely either on filters designed to respond to ideal cylindrical structures, which lose accuracy when the lin ...

2014

LiftPose3D, a deep learning-based approach for transforming two-dimensional to three-dimensional poses in laboratory animals

Pascal Fua, Pavan P Ramdya, Helge Jochen Rhodin, Semih Günel, Victor Lobato Rios, Adám Gosztolai, Daniel Eduardo Morales Garza

LiftPose3D infers three-dimensional poses from two-dimensional data or from limited three-dimensional data. The approach is illustrated for videos of behaving Drosophila, mice, rats and macaques. ...

Nature Publishing Group2021

Deformation-aware Unpaired Image Translation for Pose Estimation on Laboratory Animals

Pascal Fua, Pavan P Ramdya, Helge Jochen Rhodin, Semih Günel

Our goal is to capture the pose of neuroscience model organisms, without using any manual supervision, to be able to study how neural circuits orchestrate behaviour. Human pose estimation attains remarkable accuracy when trained on real or simulated datase ...

2020

Automated Delineation of Dendritic Networks in Noisy Image Stacks

Pascal Fua, François Fleuret, Germán González Serrano

We present a novel approach to 3D delineation of dendritic networks in noisy image stacks. We achieve a level of automation beyond that of state-of-the-art systems, which model dendrites as continuous tubular structures and postulate simple appearance mode ...

Springer-Verlag2008

Exploring Ambiguities for Monocular Non-Rigid Shape Estimation

Pascal Fua

Recovering the 3D shape of deformable surfaces from single images is difficult because many different shapes have very similar projections. This is commonly addressed by restricting the set of possible shapes to linear combinations of deformation modes and ...

2010

Promoting Connectivity of Network-Like Structures by Enforcing Region Separation

Pascal Fua, Mateusz Kozinski, Doruk Oner, Leonardo Citraro

We propose a novel, connectivity-oriented loss function for training deep convolutional networks to reconstruct network-like structures, like roads and irrigation canals, from aerial images. The main idea behind our loss is to express the connectivity of r ...

2022

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 ...

IEEE2018

Are Existing Monocular Computer Vision-Based 3D Motion Capture Approaches Ready for Deployment? A Methodological Study on the Example of Alpine Skiing

Pascal Fua, Helge Jochen Rhodin

In this study, we compared a monocular computer vision (MCV)-based approach with the golden standard for collecting kinematic data on ski tracks (i.e., video-based stereophotogrammetry) and assessed its deployment readiness for answering applied research q ...

2019

Keypoint Recognition using Randomized Trees

Pascal Fua, Vincent Lepetit

In many 3--D object-detection and pose-estimation problems, run-time performance is of critical importance. However, there usually is time to train the system, which we will show to be very useful. Assuming that several registered images of the target obje ...

2006

Reconstruction of Manipulated Garment with Guided Deformation Prior

Zhantao Deng, Pascal Fua, Ren Li, Corentin Camille Marius Dumery

Modeling the shape of garments has received much attention, but most existing approaches assume the garments to be worn by someone, which constrains the range of shapes they can assume. In this work, we address shape recovery when garments are being manipu ...

2024

Wide-Depth-Range 6D Object Pose Estimation in Space

Pascal Fua, Mathieu Salzmann, Wenzel Alban Jakob, Yinlin Hu

6D pose estimation in space poses unique challenges that are not commonly encountered in the terrestrial setting. One of the most striking differences is the lack of atmospheric scattering, allowing objects to be visible from a great distance while complic ...

IEEE2021

3D Pose Based Feedback For Physical Exercises

Pascal Fua, Mathieu Salzmann, Isinsu Katircioglu, Sena Kiciroglu

Unsupervised self-rehabilitation exercises and physical training can cause serious injuries if performed incorrectly. We introduce a learning-based framework that identifies the mistakes made by a user and proposes corrective measures for easier and safer ...

Springer2022

Network Flow Integer Programming to Track Elliptical Cells in Time-Lapse Sequences

Pascal Fua, Engin Türetken, Xinchao Wang, Carlos Joaquin Becker

We propose a novel approach to automatically tracking elliptical cell populations in time-lapse image sequences. Given an initial segmentation, we account for partial occlusions and overlaps by generating an over-complete set of competing detection hypothe ...

Institute of Electrical and Electronics Engineers2017

Active Testing Search for Point Cloud Matching

Pascal Fua, Raphael Sznitman, Jan Kybic

We present a general approach for solving the point-cloud matching problem for the case of mildly nonlinear transformations. Our method quickly finds a coarse approximation of the solution by exploring a reduced set of partial matches using an approach to ...

2013

Scale-Adaptive Superpixels

Pascal Fua, Sabine Süsstrunk, Radhakrishna Achanta, Pablo Marquez Neila

Size uniformity is one of the prominent features of superpixels. However, size uniformity rarely conforms to the varying content of an image. The chosen size of the superpixels therefore represents a compromise - how to obtain the fewest superpixels withou ...

Society for Imaging Science and Technology2018

Reconstructing Loopy Curvilinear Structures Using Integer Programming

Pascal Fua, Engin Türetken, Fethallah Benmansour

We propose a novel approach to automated delineation of linear structures that form complex and potentially loopy networks. This is in contrast to earlier approaches that usually assume a tree topology for the networks. At the heart of our method is an Int ...

Ieee2013

Learning Separable Filters

Pascal Fua, Vincent Lepetit, Bugra Tekin, Roberto Rigamonti, Amos Sironi

Learning filters to produce sparse image representations in terms of overcomplete dictionaries has emerged as a powerful way to create image features for many different purposes. Unfortunately, these filters are usually both numerous and non-separable, mak ...

Ieee Computer Soc2015

Fast Part-Based Classification for Instrument Detection in Minimally Invasive Surgery

Pascal Fua, Raphael Sznitman, Carlos Joaquin Becker

Automatic visual detection of instruments in minimally invasive surgery (MIS) can significantly augment the procedure experience for operating clinicians. In this paper, we present a novel technique for detecting surgical instruments by constructing a robu ...

Springer2014

Measuring the accuracy of softball impact simulations

Pascal Fua

A study has been conducted to review viscoelastic and foam-constitutive models to describe sport ball response to impact with a rigid cylindrical surface. The impact model was developed to simulate a ball-bat collision. Comparisons were made to actual impa ...

Springer London Ltd2016