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 introduce a comprehensive benchmark for local features and robust estimation algorithms, focusing on the downstream task-the accuracy of the reconstructed camera pose-as our primary metric. Our pipeline's modular structure allows easy integration, confi ...

We propose a novel Bayesian approach to automated delineation of curvilinear structures that form complex and potentially loopy networks. By representing the image data as a graph of potential paths, we first show how to weight these paths using discrimina ...

Diffusion models generating images conditionally on text, such as Dall-E 2 [51] and Stable Diffusion[53], have recently made a splash far beyond the computer vision com- munity. Here, we tackle the related problem of generating point clouds, both unconditi ...

Modern background subtraction techniques can handle gradual illumination changes but can easily be confused by rapid ones. We propose a technique that overcomes this limitation by relying on a statistical model, not of the pixel intensities, but of the ill ...

It has recently been shown that deformable 3D surfaces could be recovered from single video streams. However, existing techniques either require a reference view in which the shape of the surface is known a priori, which often may not be available, or requ ...

We propose an approach to detect flying objects such as 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. Solving such a difficult problem re ...

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 long years of studies and development. This achievement is also an open window to a new goal: flying around the world. In the present article, we present this long and incredible story, highlighting the different steps, the technology invo

We propose a single-shot approach for simultaneously detecting an object in an RGB image and predicting its 6D pose without requiring multiple stages or having to examine multiple hypotheses. Unlike a recently proposed single-shot technique for this task [ ...

Orthographic images compose an efficient and economic way to represent aerial images. This kind of information allows to measure two-dimensional objects and relate these to Geographic Information Systems. This paper deals with the computation of a true ort ...

We have developed a method for the detection of both generic flight neighbouring aircrafts and those on a collision course. Our approach employs a sliding window linear Support Vector Machine (SVM) classifier with a Histogram of Oriented Gradients (HOG) feature representation. An extension of this approach to the spatio-temporal domain is also considered and we demonstrate its advantage for the detection of aircrafts on a collision path. We evaluated our approach for the detection of both small rotorcraft a

State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density in the image plane. While useful for this purpose, this image- plane density has no immediate physical meaning because it is subject to perspecti ...

In this paper we empirically analyze 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 experim ...

There are many approaches to weakly-supervised training of networks to segment 2D images. By contrast, existing approaches to segmenting volumetric images rely on full-supervision of a subset of 2D slices of the 3D volume. We propose an approach to volume ...

Given an image sequence featuring a portion of a sports field filmed by a moving and uncalibrated camera, such as the one of the smartphones, our goal is to compute automatically in real time the focal length and extrinsic camera parameters for each image ...

In the context of retinal microsurgery, visual tracking of instruments is a key component of robotics assistance. The difficulty of the task and major reason why most existing strategies fail on {\it in-vivo} image sequences lies in the fact that complex a ...

We propose a method for the unsupervised reconstruction of a temporally-coherent sequence of surfaces from a sequence of time-evolving point clouds, yielding dense, semantically meaningful correspondences between all keyframes. We represent the reconstruct ...

In this paper we apply boosting to learn complex non-linear local visual feature representations, drawing inspiration from its successful application to visual object detection. The main goal of local feature descriptors is to distinctively repre- sent a s ...

The dominant approach for learning local patch descriptors relies on small image regions whose scale must be properly estimated a priori by a keypoint detector. In other words, if two patches are not in correspondence, their descriptors will not match. A s ...

State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density. While effective, these data-driven approaches rely on large amount of data annotation to achieve good performance, which stops these models from ...

Pascal Fua

Chat with Graph Search

Image Matching Across Wide Baselines: From Paper to Practice

Reconstructing Curvilinear Networks using Path Classifiers and Integer Programming

Geometrically-Conditioned Point Diffusion Models

Making Background Subtraction Robust to Sudden Illumination Changes

Template-Free Monocular Reconstruction of Deformable Surfaces

Flying Objects Detection from a Single Moving Camera

L'Hydroptère: A story of a dream

Real-Time Seamless Single Shot 6D Object Pose Prediction

IA Generative Model for True Orthorectification

Detection of Aircrafts on a Collision Course using Spatio-Temporal HOG

Geometric and Physical Constraints for Drone-Based Head Plane Crowd Density Estimation

On the Relevance of Sparsity for Image Classification

Weakly Supervised Volumetric Image Segmentation with Deformed Templates

Real-time camera pose estimation for sports fields

Data-Driven Visual Tracking in Retinal Microsurgery

Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlases

Learning Image Descriptors with the Boosting-Trick

Beyond Cartesian Representations for Local Descriptors

Supervised Feature Learning for Curvilinear Structure Segmentation

Leveraging Self-Supervision for Cross-Domain Crowd Counting