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.

This repository contains the data used for the work "PartSDF: Part-Based Implicit Neural Representation for Composite 3D Shape Parametrization and Optimization", as well as the checkpoints of the pre-trained models. The data consists in watertight meshes, their decomposition into parts, the poses of each parts, and the train/test splits used in the main work. They consists in processed meshes from ShapeNet (for cars and chairs), using the PartNet decomposition, and mixers from HybridSDF. Note that the 3D s

Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be tackled by solving a linear least-square problem, which can be done by finding the eigenvector corresponding to the smal ...

We propose a working set based approximate subgradient descent algorithm to minimize the margin-sensitive hinge loss arising from the soft constraints in max-margin learning frameworks, such as the structured SVM. We focus on the setting of general graphic ...

We propose an automated approach to modeling drainage channels and, more generally, linear features that lie on the terrain|from multiple images. It produces models of the features and of the surrounding terrain that are accurate and consistent and requires only minimal human intervention. We take advantage of geometric constraints and photommetric knowledge. First, rivers flow downhill and lie at the bottom valleys whose floors tend to be either V- or U-shaped. Second, the drainage pattern appears in g

Relating behavior to brain activity in animals is a fundamental goal in neuroscience, with practical applications in building robust brain-machine interfaces. However, the domain gap between individuals is a major issue that prevents the training of genera ...

Efficient analysis of the three-dimensional (3D) shape and distribution of curvilinear crystal defects, namely dislocations, is an open research topic in material science and computer vision. In order to determine the structural and opto-electrical characteristics of the material, accurate 3D reconstructions of dislocations are required. In its current state, an established way to obtain 3D information of dislocations is electron tomography which relies on acquiring dozens of images from tilted sample for w

Detection of curvilinear structures in images has long been of interest. One of the most challenging aspects of this problem is inferring the graph representation of the curvilinear network. Most existing delineation approaches first perform binary segment ...

We propose two deep learning models that fully automate shape parameterization for aerodynamic shape optimization. Both models are optimized to parameterize via deep geometric learning to embed human prior knowledge into learned geometric patterns, elimina ...

We present a real-time approach for multi-person 3D motion capture at over 30 fps using a single RGB camera. It operates successfully in generic scenes which may contain occlusions by objects and by other people. Our method operates in subsequent stages. T ...

We propose a way to incorporate a priori information in a 3D stereo reconstruction process from a pair of calibrated face images. A 3D mesh modeling the surface is iteratively deformed in order to minimize an energy function. Differential information about the object shape is used to generate an adaptive mesh that can fulfil the compacity and the accuracy requirements. Moreover in areas where the stereo information is not reliable enough to accurately recover the surface shape, because of inappropriate text

Recovering a person's height from a single image is important for virtual garment fitting, autonomous driving and surveillance. However, it is also very challenging without absolute scale information. Here, we examine the rarely addressed case, where camer ...

Recovering the 3D shape of a nonrigid surface from a single viewpoint is known to be both ambiguous and challenging. Resolving the ambiguities typically requires prior knowledge about the most likely deformations that the surface may undergo. It often take ...

Binary descriptors allow faster similarity computation than real-valued ones while requiring much less storage. As a result, many algorithms have recently been proposed to binarize ﬂoating-point descriptors so that they can be searched for quickly. Unfortu ...

3D reconstruction of deformable (or non-rigid) scenes from a set of monocular 2D image observations is a long-standing and actively researched area of computer vision and graphics. It is an ill-posed inverse problem, since-without additional prior assumpti ...

Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in video sequences, and those that do only impose weak smoothness co ...

Detection of elongated structures in 2D images and 3D image stacks is a critical prerequisite in many applications and Machine Learning-based approaches have recently been shown to deliver superior performance. However, these methods essentially classify i ...

While road obstacle detection techniques have become increasingly effective, they typically ignore the fact that, in practice, the apparent size of the obstacles decreases as their distance to the vehicle increases. In this letter, we account for this by c ...

Our goal is to reconstruct both the shape and reflectance properties of surfaces from multiple images. To this end, we introduce an object-centered representation, specifically, a hexagonally-connected 3-D mesh of vertices with triangular facets. Such a representation accommodates the two classes of information mentioned above, as well as multiple images, self-occlusions and geometric constraints. We have chosen to model the surface material using the Lambertian reflectance model with variable albedo. Conse

Curvilinear structures frequently appear in microscopy imaging as the object of interest. Crystallographic defects, i.e dislocations, are one of the curvilinear structures that have been repeatedly investigated under transmission electron microscopy (TEM) ...

Thanks to recent advancements in image processing and deep learning techniques, visual surface inspection in production lines has become an automated process as long as all the defects are visible in a single or a few images. However, it is often necessary ...

Pascal Fua

Chat with Graph Search

Dataset for "PartSDF: Part-Based Implicit Neural Representation for Composite 3D Shape Parametrization and Optimization"

Eigendecomposition-Free Training of Deep Networks for Linear Least-Square Problems

Learning for Structured Prediction Using Approximate Subgradient Descent with Working Sets

Fast, Accurate and Consistent Modeling of Drainage and Surrounding Terrain

Overcoming the Domain Gap in Neural Action Representations

Structure-aware Multi-view 3D Reconstruction of Dislocations in TEM with Message Passing Neural Networks

Joint Segmentation and Path Classification of Curvilinear Structures

Automatic Parameterization for Aerodynamic Shape Optimization via Deep Geometric Learning

XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera

Using differential constraints to generate a 3D face model from stereo

What Face and Body Shapes Can Tell Us About Height

Linear Local Models for Monocular Reconstruction of Deformable Surfaces

Thick Boundaries in Binary Space and Their Influence on Nearest-Neighbor Search

State of the Art in Dense Monocular Non-Rigid 3D Reconstruction

Counting People by Estimating People Flows

Projection onto the Manifold of Elongated Structures for Accurate Extraction

Perspective Aware Road Obstacle Detection

Object-Centered Surface Reconstruction: Combining Multi-Image Stereo and Shading

3D reconstruction of curvilinear structures with stereo matching deep convolutional neural networks

Defect segmentation for multi-illumination quality control systems