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.

Given two to four synchronized video streams taken at eye level and from different angles, we show that we can effectively combine a generative model with dynamic programming to accurately follow up to six individuals across thousands of frames in spite of ...

In addition to impressive performance, vision transformers have demonstrated remarkable abilities to encode information they were not trained to extract. For example, this information can be used to perform segmentation or single-view depth estimation even though the networks were only trained for image recognition. We show that a similar phenomenon occurs when explicitly training transformers for semantic segmentation in a supervised manner for a set of categories: Once trained, they provide valuable infor

Optical motion capture provides an impressive ability to replicate gestures. However, even with a highly professional system there are many instances where crucial markers are occluded or when the algorithm confuses the trajectory of one marker with that of another. This requires much editing work on the user's part before the complete animation is ready for use. Here, the authors present an approach to increasing the robustness of a motion capture system by using an anatomical human model. It includes a re

Mean Field inference is central to statistical physics. It has attracted much interest in the Computer Vision community to efficiently solve problems expressible in terms of large Conditional Random Fields. However, since it models the posterior probabilit ...

We present an efficient matching method for generalized geometric graphs. Such graphs consist of vertices in space connected by curves and can represent many real world structures such as road networks in remote sensing, or vessel networks in medical imagi ...

In 2009, l’Hydroptère broke the symbolic barrier of 50 knots and became the world fastest sailing boat over both 500 meters and 1 nautical mile. This major achievement relied on the high skills of the sailing team but also on technical advances of the boat, resulting from the scientific collaboration between the Hydroptère Design Team and the Ecole Polytechnique Fédérale de Lausanne (EPFL). In the present article, we highlight the multidisciplinary research activity performed within EPFL in the course of th

In this paper we propose an unsupervised feature extraction method to capture temporal information on monocular videos, where we detect and encode subject of interest in each frame and leverage contrastive self-supervised (CSS) learning to extract rich lat ...

We present a multi-view change detection approach aimed at being robust with respect to common “disturbance factors” yielding image changes in realworld applications. Disturbance factors causing “slow” or “fast-and-global” image variations, such as light c ...

We present a real-time system that can draw virtual patterns or images on deforming real objects by estimating both the deformations and the shading parameters. We show that this is what is required to render the virtual elements so that they blend convinc ...

In this paper we analyze empirically the importance of sparsifying representations for classification purposes. We focus on those obtained by convolving images with linear filters, which can be either hand designed or learned, and perform extensive experiments on two important Computer Vision problems, image categorization and pixel classification. To this end, we adopt a simple modular architecture that encompasses many recently proposed models. The key outcome of our investigations is that enforcing spars

State-of-the-art methods for self-supervised sequential action alignment rely on deep networks that find correspon- dences across videos in time. They either learn frame-to- frame mapping across sequences, which does not leverage temporal information, or a ...

This document describes an ITK implementation of an interactive method for tracing curvilinear structures. The basic tools provided in this framework are an oriented flux-based tubularity measure and a geodesic path tracer that uses the fast marching algor ...

We propose an approach to incorporating dynamic models into the human body tracking process that yields full 3--D reconstructions from monocular sequences. We formulate the tracking problem is terms of minimizing a differentiable criterion whose differential structure is rich enough for successful optimization using a single-hypothesis hill-climbing approach as opposed to a multi-hypotheses probabilistic one. In other words, we avoid the computational complexity of multi-hypotheses algorithms while obtainin

Classical semantic segmentation methods, including the recent deep learning ones, assume that all classes observed at test time have been seen during training. In this paper, we tackle the more realistic scenario where unexpected objects of unknown classes ...

We propose an approach to reconstructing tree structures that evolve over time in 2D images and 3D image stacks such as neuronal axons or plant branches. Instead of reconstructing structures in each image independently, we do so for all images simultaneous ...

We show that we can effectively fit arbitrarily complex animation models to noisy image data. 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. They can then be fed to existing an

This paper describes the European Commission Framework 7 funded project myCopter (2011-2014). The project is still at an early stage so the paper starts with the current transportation issues faced by developed countries and describes a means to solve them through the use of personal aerial transportation. The concept of personal air vehicles (PAV) is briefly reviewed and how this project intends to tackle the problem from a different perspective described. It is argued that the key reason that many PAV con

If we are ever to unravel the mysteries of brain function at its most fundamental level, we will need a precise understanding of how its component neurons connect to each other. Electron Microscopes (EM) can now provide the nanometer resolution that is nee ...

Being able to recover the shape of 3D deformable surfaces from a single video stream would make it possible to field reconstruction systems that run on widely available hardware without requiring specialized devices. However, because many different 3D shapes can have virtually the same projection, such monocular shape recovery is inherently ambiguous. In this survey, we will review the two main classes of techniques that have proved most effective so far: The template-based methods that rely on establishing

Superpixels are becoming increasingly popular for use in computer vision applications. However, there are few algorithms that output a desired number of regular, compact superpixels with a low computational overhead. We introduce a novel algorithm that clusters pixels in the combined five-dimensional color and image plane space to efficiently generate compact, nearly uniform superpixels. The simplicity of our approach makes it extremely easy to use -- a lone parameter specifies the number of superpixels --

Pascal Fua

Chat with Graph Search

Multi-Camera People Tracking with a Probabilistic Occupancy Map

AttEntropy: On the Generalization Ability of Supervised Semantic Segmentation Transformers to New Objects in New Domains

Using skeleton-based tracking to increase the reliability of optical motion capture

Multi-Modal Mean-Fields via Cardinality-Based Clamping

Geometric Graph Matching Using Monte Carlo Tree Search

L'HYDROPTERE: HOW MULTIDISCIPLINARY SCIENTIFIC RESEARCH MAY HELP BREAK THE SAILING SPEED RECORD

Temporal Representation Learning on Monocular Videos for 3D Human Pose Estimation

Robust Multi-View Change Detection

Augmenting Deformable Objects in Real-Time

On the Relevance of Sparsity for Image Classification

Learning to Align Sequential Actions in the Wild

Tubular Geodesics using Oriented Flux: An ITK Implementation

Monocular 3-D Tracking of the Golf Swing

Detecting the Unexpected via Image Resynthesis

Reconstructing Evolving Tree Structures in Time Lapse Sequences

From regular images to animated heads: a least squares approach

myCopter – Enabling Technologies for Personal Aerial Transportation Systems

Modeling Brain Circuitry over a Wide Range of Scales

Deformable Surface 3D Reconstruction from Monocular Images

SLIC Superpixels