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.

We develop a deep architecture to learn to find good correspondences for wide-baseline stereo. Given a set of putative sparse matches and the camera intrinsics, we train our network in an end-to-end fashion to label the correspondences as inliers or outlie ...

We combine detection and tracking techniques to achieve robust 3-D motion recovery of people seen from arbitrary viewpoints by a single and potentially moving camera. We rely on detecting key postures, which can be done reliably, using a motion model to in ...

Recently, parametric mappings have emerged as highly effective surface representations, yielding low reconstruction error. In particular, the latest works represent the target shape as an atlas of multiple mappings, which can closely encode object parts. A ...

Detection of surgical instruments plays a key role in ensuring patient safety in minimally invasive surgery. In this paper, we present a novel method for 2D vision-based recognition and pose estimation of surgical instruments that generalizes to different ...

Aerodynamic shape optimization has many industrial applications. Existing methods, however, are so computationally demanding that typical engineering practices are to either simply try a limited number of hand-designed shapes or restrict oneself to shapes ...

In this paper, we show that tracking different kinds of interacting objects can be formulated as a network-flow Mixed Integer Program. This is made possible by tracking all objects simultaneously and expressing the fact that one object can appear or disapp ...

Existing data-driven methods for draping garments over human bodies, despite being effective, cannot handle garments of arbitrary topology and are typically not end-to-end differentiable. To address these limitations, we propose an end-to-end differentiabl ...

Many state-of-the-art segmentation algorithms rely on Markov or Conditional Random Field models designed to enforce spatial and global consistency constraints. This is often accomplished by introducing additional latent variables to the model, which can greatly increase its complexity. As a result, estimating the model parameters or computing the best maximum a posteriori (MAP) assignment becomes a computationally expensive task.

The aim of this work is to present an approach that can help to characterize teams’ and players’ tactical behavior using two techniques to aid handball coaches to assess tactical procedures when using spatial measures derived from players position data. Results suggest that it is possible to identify tactical spatial differences between fast-break and fast throw-off. The approach presented in this work may be useful to reduce the time spent in game analysis and to improve coaches’ assessment of tactical per

In this report, we show that facial descriptors can be used very effectively in conjunction with a tracklet-based multi-person tracker both to localize and to identify or re-identify people over long sequences. Thus, we can reliably deliver both trajectories and identities in crowded scenes. Furthermore, the whole approach is fast enough to be implemented in real-time. Our key insight is that this can be done even though the faces can only be recognized relatively infrequently.

Multiple human 3D pose estimation from multiple camera views is a challenging task in unconstrained environments. Each individual has to be matched across each view and then the body pose has to be estimated. Additionally, the body pose of every individual ...

Many approaches to draping individual garments on human body models are realistic, fast, and yield outputs that are differentiable with respect to the body shape on which they are draped. However, they are either unable to handle multi-layered clothing, wh ...

Pascal Fua

Chat with Graph Search

Detecting Irregular Curvilinear Structures in Gray Scale and Color Imagery using Multi-Directional Oriented Flux

Learning to Find Good Correspondences

Learning Separable Filters

Bridging the Gap between Detection and Tracking for 3D Monocular Video-Based Motion Capture

A Closed-Form Pairwise Solution to Local Non-Rigid Structure-from-Motion

3D people tracking with Gaussian process dynamical models

Better Patch Stitching for Parametric Surface Reconstruction

Simultaneous Recognition and Pose Estimation of Instruments in Minimally Invasive Surgery

Geodesic Convolutional Shape Optimization

Tracking Interacting Objects Optimally Using Integer Programming

DIG: Draping Implicit Garment over the Human Body

ImplicitAtlas: Learning Deformable Shape Templates in Medical Imaging

Are Spatial and Global Constraints Really Necessary for Segmentation?

Tracking Multiple Handball Players using Multi-Commodity Network Flow for Assessing Tactical Behavior

Pareto-optimal Dictionaries for Signatures

Hybrid Algorithms for the Minimum-Weight Rooted Arborescence Problem

Compact Signatures for High-speed Interest Point Description and Matching

Facial Descriptors for Identity-Preserving Multiple People Tracking

Multiple Human Pose Estimation with Temporally Consistent 3D Pictorial Structures

ISP: Multi-Layered Garment Draping with Implicit Sewing Patterns