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.

Neural Radiance Fields (NeRF) has emerged as a compelling framework for scene representation and 3D recovery. To improve its performance on real-world data, depth regularizations have proven to be the most effective ones. However, depth estimation models not only require expensive 3D supervision in training, but also suffer from generalization issues. As a result, the depth estimations can be erroneous in practice, especially for outdoor unbounded scenes. In this paper, we propose to employ view-consistent

Accurate 3D models of the human heart require not only correct outer surfaces but also realistic inner structures, such as the ventricles, atria, and myocardial layers. Approaches relying on implicit surfaces, such as signed distance functions (SDFs), are primarily designed for single watertight surfaces, making them ill-suited for multi-layered anatomical structures. They often produce gaps or overlaps in shared boundaries. Unsigned distance functions (UDFs) can model non-watertight geometries but are hard

We present a method that estimates in real-time and under challenging conditions the 3D pose of a known object. Our method relies only on grayscale images since depth cameras fail on metallic objects; it can handle poorly textured objects, and cluttered, c ...

This paper performs a comprehensive and comparative evaluation of the state of the art local features for the task of image based 3D reconstruction. The evaluated local features cover the recently developed ones by using powerful machine learning technique ...

We introduce a classification-based approach to finding occluding texture boundaries. The classifier is composed of a set of weak lear ners which operate on image intensity discriminative features which are defined on small patches and fast to compute. A d ...

Linear crystal defects called dislocations are one of the most fascinating concepts in materials science that govern mechanical and optoelectronic properties of many materials across a broad range of application. Three-dimensional (3-D) study of dislocation network is in principle accessible by conventional tomographic and stereoscopic techniques in Transmission Electron Microscopy (TEM). In these techniques in general the need to tilt the specimen for acquiring image series over large tilt ranges remain ho

Accurate 3D human pose estimation from single images is possible with sophisticated deep-net architectures that have been trained on very large datasets. However, this still leaves open the problem of capturing motions for which no such database exists. Ma ...

We propose a fully automated approach to calibrating multiple cameras whose fields of view may not all overlap. Our technique only requires waving an arbitrary textured planar pattern in front of the cameras, which is the only manual intervention that is r ...

In this paper, we show that, given video sequences of a moving person acquired with a multi-camera system, we can track joint locations during the movement and recover shape information. We outline techniques for fitting a simplified model to the noisy 3-D data extracted from the images and a new tracking process based on least squares matching is presented. The recovered shape and motion parameters can be used to either reconstruct the original sequence or to allow other animation models to mimic the subje

Scanning Electron Microscopy (SEM) is an invaluable tool for biologists and neuroscientists to study brain structure at the intra- cellular level. While able to image tissue samples with up to 5nm isotropic resolution, image acquisition is prohibitively sl ...

Deformable 3--D models are used extensively in Computer Graphics and Computer Vision for Visualization, Animation and Modeling. They can be represented either as traditional explicit surfaces, such as triangulated meshes, or as implicit surfaces. Explicit surface representations are widely accepted because they are simple to deform and render. However, for fitting purposes, they suffer from the fact that using them typically involves minimizing a non-differentiable distance function. By contrast, implicit s

Recovering the 3D shape of deformable surfaces from single images is known to be a highly ambiguous problem because many different shapes may have very similar projections. This is commonly addressed by restricting the set of possible shapes to linear comb ...

Eigendecomposition of symmetric matrices is at the heart of many computer vision algorithms. However, the derivatives of the eigenvectors tend to be numerically unstable, whether using the SVD to compute them analytically or using the Power Iteration (PI) ...

We explore an approach to 3D people tracking with learned motion models and deterministic optimization. The tracking problem is formulated as the minimization of a differ- entiable criterion whose differential structure is rich enough for optimization to be accom- plished via hill-climbing. This avoids the computational expense of Monte Carlo methods, while yielding good results under challenging conditions. To demonstrate the generality of the approach we show that we can learn and track cyclic motions suc

In earlier work~\cite{Lepetit04b}, we proposed to treat wide baseline matching of feature points as a classification problem and proposed an implementation based on K-means and nearest neighbor classification. We showed that this method is both reliable and faster than competing methods, but still too slow for real-time implementations. Here we show that using decision trees instead speeds up the computation greatly, while increasing the robustness. This allows point matching under large viewpoint and illum

Generative models that produce point clouds have emerged as a powerful tool to represent 3D surfaces, and the best current ones rely on learning an ensemble of parametric representations. Unfortunately, they offer no control over the deformations of the su ...

We propose a non-iterative solution to the PnP problem-the estimation of the pose of a calibrated camera from n 3D-to-2D point correspondences-whose computational complexity grows linearly with n. This is in contrast to state-of-the-art methods that are O( ...

We present a new approach for matching sets of branching curvilinear structures that form graphs embedded in R2 or R3 and may be subject to deformations. Unlike earlier methods, ours does not rely on local appearance similarity nor does require a good init ...

Most recent approaches to monocular 3D pose estimation rely on Deep Learning. They either train a Convolutional Neural Network to directly regress from image to 3D pose, which ignores the dependencies between human joints, or model these dependencies via a ...

Systems and methods for tracking interacting objects may acquire, with a sensor, and two or more images associated with two or more time instances. A processor may generate image data from the two or more images. The processor may apply an extended Probabi ...

Pascal Fua

Chat with Graph Search

A View-consistent Sampling Method for Regularized Training of Neural Radiance Fields

Pairwise-Constrained Implicit Functions for 3D Human Heart Modeling

A Novel Representation of Parts for Accurate 3D Object Detection and Tracking in Monocular Images

A Performance Evaluation of Local Features for Image-Based 3D Reconstruction

Classification-based Probabilistic Modeling of Texture Transition for Fast Line Search Tracking and Delineation

Three-dimensional electron imaging of dislocations from a single sample tilt

Learning Monocular 3D Human Pose Estimation from Multi-view Images

An all-in-one solution to geometric and photometric calibration

Modeling human bodies from video sequences

Flash Scanning Electron Microscopy

Implicit Meshes for Surface Reconstruction

Stochastic Exploration of Ambiguities for Non-Rigid Shape Recovery

Robust Differentiable SVD

Temporal Motion Models for Monocular and Multiview 3–D Human Body Tracking

Towards Recognizing Feature Points using Classification Trees

Shape Reconstruction by Learning Differentiable Surface Representations

EPnP: An Accurate O(n) Solution to the PnP Problem

Non-Rigid Graph Registration using Active Testing Search

Structured Prediction of 3D Human Pose with Deep Neural Networks

Systems and methods for tracking interacting objects