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 propose a novel approach to point matching under large viewpoint and illumination changes that is suitable for accurate object pose estimation at a much lower computational cost than state-of-the-art methods. Most of these methods rely either on using ad hoc local descriptors or on estimating local affine deformations. By contrast, we treat wide baseline matching of keypoints as a classification problem, in which each class corresponds to the set of all possible views of such a point. Given one or more i

This paper describes the European Commission (EC) Framework 7 funded project myCopter (2011-2014). The project is still at an early stage so the paper starts with a discussion of the current transportation issues faced, for example, by European countries and describes a means to solve them through the use of a personal aerial transportation system (PATS). The concept of personal air vehicles (PAVs) is briefly reviewed and how this project intends to tackle the problem described. It is argued that the key re

In this Technical Report we propose a set of improvements with respect to the KernelBoost classifier presented in [Becker et al., MICCAI 2013]. We start with a scheme inspired by Auto-Context, but that is suitable in situations where the lack of large training sets poses a potential problem of overfitting. The aim is to capture the interactions between neighboring image pixels to better regularize the boundaries of segmented regions. As in Auto-Context [Tu et al., PAMI 2009] the segmentation process is iter

While supervised object detection and segmentation methods achieve impressive accuracy, they generalize poorly to images whose appearance significantly differs from the data they have been trained on. To address this when annotating data is prohibitively e ...

Vehicles can encounter a myriad of obstacles on the road, and it is impossible to record them all beforehand to train a detector. Instead, we select image patches and inpaint them with the surrounding road texture, which tends to remove obstacles from thos ...

We present an effective method to optimize over the parameters of an image patch descriptor to obtain one that is computationally more efficient while maintaining a high recognition rate. We formulate the optimization problem in a multi-objective manner, which balances two conflicting goals while removing the need for traditional weighting coefficients. To this end we introduce the Pareto efficiency criterion, which helps finding solutions that increase one objective without decreasing the other. Despite th

Even the best current algorithms for estimating body 3D shape and pose yield results that include body self- intersections. In this paper, we present CLOAF, which exploits the diffeomorphic nature of Ordinary Differential Equations to eliminate such self-i ...

We show that we can effectively fit arbitrarily complex animation models to noisy data extracted from ordinary face images. Our approach is based on least-squares adjustment, using of a set of progressively finer control triangulations and takes advantage of three complementary sources of information: stereo data, silhouette edges, and 2D feature points. In this way, complete head models - including ears and hair - can be acquired with a cheap and entirely passive sensor, such as an ordinary video camera. T

Supervised approaches to 3D pose estimation from single images are remarkably effective when labeled data is abundant. However, as the acquisition of ground-truth 3D labels is labor intensive and time consuming, recent attention has shifted towards semi- a ...

We propose an approach for detecting flying objects such as Unmanned Aerial Vehicles (UAVs) and aircrafts when they occupy a small portion of the field of view, possibly moving against complex backgrounds, and are filmed by a camera that itself moves. We a ...

This real-time augmented reality demonstration relies on our tracking algorithm described in V. Lepetit et al (2003). This algorithm considers natural feature points, and then does not require engineering of the environment. It merges the information from preceding frames in traditional recursive tracking fashion with that provided by a very limited number of reference frames. This combination results in a system that does not suffer from jitter and drift, and can deal with drastic changes. The tracker reco

State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density. They typically use the same filters over the whole image or over large image patches. Only then do they estimate local scale to compensate for p ...

Our demo demonstrates the method we published at CVPR this year for tracking specular and poorly textured objects, and lets the visitors experiment with it and with their own patterns. Our approach only requires a standard monocular camera (no need for a d ...

We show that we can effectively fit complex animation models to noisy image data. Our approach is based on robust least squares adjustment and takes advantage of three complementary sources of information: stereo data, silhouette edges and 2D feature points. We take stereo to be our main information source and use the other two whenever available. In this way, complete head models-including ears and hair-can be acquired with a cheap and entirely passive sensor, such as an ordinary video camera. The motion p

This survey focuses on a class of methods for image alignment based on a global, iterative optimization. We synthetically describe the existing methods (included the recent Efficient Second Order Method), compare their theoretical aspects, computational costs and implementation issues, and finally present an example of application to 3D tracking, involving a complex, non-linear warp.

Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be solved by ﬁnding the eigenvector corresponding to the smallest, or zero, eigenvalue of a matrix representing a linear sy ...

We describe in this document our preliminary results regarding the tracking of dendrites spreading from a neuron in confocal microscope im- ages. When using a small number of image layers, we obtain good results by combining a EM-based local estimate of the probability that an image pixel belongs to a neuron filament with the global tree properties of the complete set of dendrites. The optimal tree is obtained with a modified minimum-spanning tree procedure. We will argue that this approach extends naturall

We propose a new variational inference method based on a proximal framework that uses the Kullback-Leibler (KL) divergence as the proximal term. We make two contributions towards exploiting the geometry and structure of the variational bound. Firstly, we propose a KL proximal-point algorithm and show its equivalence to variational inference with natural gradients (e.g. stochastic variational inference). Secondly, we use the proximal framework to derive efficient variational algorithms for non-conjugate mode

Although tracing linear structures in 2D images and 3D image stacks has received much attention over the years, full automation remains elusive. In this paper, we formulate the delineation problem as one of solving a Quadratic Mixed Integer Program (Q-MIP) ...

Representing motions as linear sums of principal components has become a widely accepted animation technique. While powerful, the simplest version of this approach is not particularly well suited to modeling the specific style of an individual whose motion had not yet been recorded when building the database: it would take an expert to adjust the PCA weights to obtain a motion style that is indistinguishable from his. Consequently, when realism is required, the current practice is to perform a full motion c

Pascal Fua

Chat with Graph Search

Point Matching as a Classification Problem for Fast and Robust Object Pose Estimation

myCopter – Enabling Technologies for Personal Aerial Transportation Systems.

Beyond KernelBoost

Self-supervised Segmentation via Background Inpainting

Detecting Road Obstacles by Erasing Them

Pareto-optimal Dictionaries for Signatures

CLOAF: CoLlisiOn-Aware Human Flow

Animated heads from ordinary images: a least-squares approach

On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation

Detecting Flying Objects using a Single Moving Camera

Real-time augmented face

Context-Aware Crowd Counting

[DEMO] Tracking Texture-less, Shiny Objects with Descriptor Fields

From synthesis to analysis: fitting human animation models to image data

Dense Methods for Image Alignment with an Application to 3D Tracking

Eigendecomposition-free Training of Deep Networks with Zero Eigenvalue-based Losses

Dendrite Tracking in Microscopic Images using Minimum Spanning Trees and Localized E-M

Kullback-Leibler Proximal Variational Inference

Automated Reconstruction of Tree Structures using Path Classifiers and Mixed Integer Programming

Style-based Motion Synthesis