Publications by Pascal Fua | EPFL Graph Search

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

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 ...

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 ...

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 ...

In this paper, we show that tracking multiple people whose paths may intersect can be formulated as a multi-commodity network flow problem. Our proposed framework is designed to exploit image appearance cues to prevent identity switches. Our method is effe ...

We propose a new learning strategy for object detection. 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 base ...

We present an augmented reality system that relies on purely passive techniques to solve the real-time registration problem. It can run on a portable PC and does not require engineering of the environment, for example by adding markers. To achieve this result, we have integrated robust computer vision techniques into a powerful VR framework. The resulting AR system allows us to produce complex rendering and animation of virtual human characters, and to blend them into the real world. The system tracks the 3

The accuracy of monocular 3D human pose estimation depends on the viewpoint from which the image is captured. While freely moving cameras, such as on drones, provide control over this viewpoint, automatically positioning them at the location which will yie ...

We present an algorithm for clustering sets of detected interest points into groups that correspond to visually distinct structure. Through the use of a suitable colour and texture representation, our clustering method is able to identify keypoints that be ...

We present a novel algorithm for the simultaneous segmentation and anatomical labeling of the cerebral vasculature. Unlike existing approaches that first attempt to obtain a good segmentation and then perform labeling, we optimize for both by simultaneousl ...

Human motion prediction is a necessary component for many applications in robotics and autonomous driving. Recent methods propose using sequence-to-sequence deep learning models to tackle this problem. However, they do not focus on exploiting different tem ...

Binary keypoint descriptors provide an efficient alternative to their floating-point competitors as they enable faster processing while requiring less memory. In this paper, we propose a novel framework to learn an extremely compact binary descriptor we ca ...

The articulated body models used to represent human motion typically have many degrees of freedom, usually expressed as joint angles that are highly correlated. The true range of motion can therefore be represented by latent variables that span a low-dimen ...

Surrogate-based optimization is widely used for aerodynamic shape optimization, and its effectiveness depends on representative sampling of the design space. However, traditional sampling methods are hard-pressed to effectively sample high-dimensional desi ...

We propose a non-iterative solution to the PnP problem-the estimation of the pose of a calibrated camera from n 3D-to-2D point correspondences-whose computational complexity grows linearly with n. This is in contrast to state-of-the-art methods that are O(n(5)) or even O(n(8)), without being more accurate. Our method is applicable for all n >= 4 and handles properly both planar and non-planar configurations. Our central idea is to express the n 3D points as a weighted sum of four virtual control points. The

High-temperature latent heat thermal energy storage with metallic alloy phase change materials (PCMs) utilize the high latent heat and high thermal conductivity to gain a competitive edge over existing sensible and latent storage technologies. Novel macrop ...

We propose an approach to overcome the two main challenges of 3D multiview object detection and localization: The variation of object features due to changes in the viewpoint and the variation in the size and aspect ratio of the object. Our approach procee ...

Most state-of-the-art approaches to road extraction from aerial images rely on a CNN trained to label road pixels as foreground and remainder of the image as background. The CNN is usually trained by minimizing pixel-wise losses, which is less than ideal t ...

To increase the reliability of existing human motion tracking algorithms, we propose a method for imposing limits on the underlying hierarchical joint structures in a way that is true to life. Unlike most existing approaches, we explicitly represent dependencies between the various degrees of freedom and derive these limits from actual experimental data. To this end, we use quaternions to represent individual 3 DOF joint rotations and Euler angles for 2 DOF rotations, which we have experimentally sampled us

While Machine Learning algorithms are key to automating organelle segmentation in large EM stacks, they require annotated data, which is hard to come by in sufficient quantities. Furthermore, images acquired from one part of the brain are not always repres ...

We introduce an approach to learning convolution filters whose joint output can be fed to a classifier that labels them as belonging to linear structures or not. The filters are learned using sparse synthesis techniques but we show that enforcing constraints is not required at run-time to achieve good classification performance. In practice, this is important as it drastically reduces the computational cost. We show that our approach outperforms the state-of-the-art on difficult, and very different, images

Pascal Fua

Chat with Graph Search

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

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

Latent Representation of CFD Meshes and Application to Airfoil Aerodynamics

Multi-Commodity Network Flow for Tracking Multiple People

A Real-Time Deformable Detector

Stable Real-Time Interaction Between Virtual Humans and Real Scenes

ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion Capture

Appearance-based Keypoint Clustering

Simultaneous segmentation and anatomical labeling of the cerebral vasculature

Motion Prediction Using Temporal Inception Module

Boosting Binary Keypoint Descriptors

Observable Subspaces for 3D Human Motion Recovery

DiffAirfoil: An Efficient Novel Airfoil Sampler Based on Latent Space Diffusion Model for Aerodynamic Shape Optimization

Accurate non-iterative O(n) solution to the PnP problem

Geodesic Convolutional Neural Network Characterization of Macro-Porous Latent Thermal Energy Storage

Pose Estimation for Category Specific Multiview Object Localization

TopoAL: An Adversarial Learning Approach for Topology-Aware Road Segmentation

Hierarchical Implicit Surface Joint Limits for Human Body Tracking

Scalable Unsupervised Domain Adaptation for Electron Microscopy

Filter Learning for Linear Structure Segmentation