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 show that by extending the Laplacian formalism, which was first introduced in the Graphics community to regularize 3D meshes, we can turn the monocular 3D shape reconstruction of a deformable surface given correspondences with a reference image into a w ...

Identity Switching remains one of the main difficulties Multiple Object Tracking (MOT) algorithms have to deal with. Many state-of-the-art approaches now use sequence models to solve this problem but their training can be affected by biases that decrease t ...

We propose a novel approach to synthesizing images that are effective for training object detectors. Starting from a small set of real images, our algorithm estimates the rendering parameters required to synthesize similar images given a coarse 3D model of ...

In this paper, we show that a better performance can be achieved by training a keypoint detector to only find those points that are suitable to the needs of the given task. We demonstrate our approach in an urban environment, where the keypoint detector should focus on stable man-made structures and ignore objects that undergo natural changes such as vegetation and clouds. We use Wald-Boost learning with task specific training samples in order to train a keypoint detector with this capability. We show that

We introduce a novel Deep Network architecture that implements the full feature point handling pipeline, that is, detection, orientation estimation, and feature description. While previous works have successfully tackled each one of these problems individu ...

Most state-of-the-art approaches to image segmentation formulate the problem using Conditional Random Fields. These models typically include a unary term and a pairwise term, whose parameters must be carefully chosen for optimal performance. Recently, stru ...

We propose the first real-time system for the egocentric estimation of 3D human body pose in a wide range of unconstrained everyday activities. This setting has a unique set of challenges, such as mobility of the hardware setup, and robustness to long capt ...

The Skinned Multi-Person Linear (SMPL) model represents human bodies by mapping pose and shape parameters to body meshes. However, not all pose and shape parameter values yield physically-plausible or even realistic body meshes. In other words, SMPL is und ...

Binary descriptors are becoming increasingly popular as a means to compare feature points very fast and while requiring comparatively small amounts of memory. The typical approach to creating them is to first compute floating-point ones, using an algorithm ...

Given three or four synchronized videos taken at eye level and from different angles, we show that we can effectively use dynamic programming to accurately follow up to six individuals across thousands of frames in spite of significant occlusions. In addit ...

Trajectories of objects are estimated by determining the optimal solution(s) of a tracking model on the basis of an occupancy probability distribution. The occupancy probability distribution is the probability of presence of objects over a set of discrete ...

In this paper, we show that tracking different kinds of interacting objects can be formulated as a network-flow Mixed Integer Program. This is made possible by tracking all objects simultaneously using intertwined flow variables and expressing the fact tha ...

Most state-of-the-art deep geometric learning single-view reconstruction approaches rely on encoder-decoder architectures that output either shape parametrizations or implicit representations. However, these representations rarely preserve the Euclidean st ...

We tackle unsupervised domain adaptation by accounting for the fact that different domains may need to be processed differently to arrive to a common feature representation effective for recognition. To this end, we introduce a deep learning framework wher ...

Shape priors have long been known to be effective when reconstructing 3D shapes from noisy or incomplete data. When using a deep-learning based shape representation, this often involves learning a latent representation, which can be either in the form of a ...

It has been shown that the 3D shape of a deformable surface in an image can be recovered by establishing correspondences between that image and a reference one in which the shape is known. These matches can then be used to set-up a convex optimization prob ...

Algorithms designed to estimate 3D pose in video sequences enforce temporal consistency but typically overlook an important source of information: The 3D pose of an object, be it rigid or articulated, has a direct influence on its direction of travel. In t ...

The performance of a classifier trained on data coming from a specific domain typically degrades when applied to a related but different one. While annotating many samples from the new domain would address this issue, it is often too expensive or impractic ...

Pascal Fua

Chat with Graph Search

Template-based Monocular 3D Shape Recovery using Laplacian Meshes

Eliminating Exposure Bias and Metric Mismatch in Multiple Object Tracking

On Rendering Synthetic Images for Training an Object Detector

Training for Task Specific Keypoint Detection

Laplacian Meshes for Monocular 3D Shape Recovery

LIFT: Learned Invariant Feature Transform

Structured Image Segmentation using Kernelized Features

Mo(2)Cap(2): Real-time Mobile 3D Motion Capture with a Cap-mounted Fisheye Camera

Adversarial Parametric Pose Prior

BRIEF: Computing a Local Binary Descriptor Very Fast

Robust People Tracking with Global Trajectory Optimization

Method and apparatus for multiple object tracking with k-shortest paths

Tracking Interacting Objects Using Intertwined Flows

UCLID-Net: Single View Reconstruction in Object Space

An Investigation of Model Bias in 3D Face Tracking

Domain-Adaptive Multibranch Networks

Deep Active Latent Surfaces for Medical Geometries

Simultaneous Point Matching and 3D Deformable Surface Reconstruction

Linking Pose and Motion

Beyond Sharing Weights for Deep Domain Adaptation