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.

Efficient and accurate segmentation of cellular structures in microscopic data is an essential task in medical imaging. Many state-of-the-art approaches to image segmentation use structured models whose parameters must be carefully chosen for optimal perfo ...

While feature point recognition is a key component of modern approaches to object detection, existing approaches require computationally expensive patch preprocessing to handle perspective distortion. In this paper, we show that formulating the problem in ...

We present a novel algorithm for the simultaneous segmentation and anatomical labeling of the cerebral vasculature. The method first constructs an over-complete graph capturing the vasculature. It then selects and labels the subset of edges that most likel ...

We combine detection and tracking techniques to achieve robust 3D motion recovery of people seen from arbitrary viewpoints by a single and potentially moving camera. We rely on detecting key postures, which can be done reliably, using a motion model to inf ...

The homography between pairs of images are typically computed from the correspondence of keypoints, which are established by using image descriptors. When these descriptors are not reliable, either because of repetitive patterns or large amounts of clutter ...

Identifying a precise anatomic skeleton is important in order to ensure high-quality motion capture. In this paper, we discuss two skeleton-fitting techniques based on 3D optical marker data. First, a local technique is proposed, based on relative marker trajectories. Then it is compared to a global optimization of a skeleton model. Various proposals are made to handle the skin deformation problem

We present a closed-form solution to the problem of recovering the 3D shape of a non-rigid inelastic surface from 3D-to-2D correspondences. This lets us detect and reconstruct such a, surface by matching individual images against a reference configuration, ...

Local feature frameworks are difficult to learn in an end-to-end fashion, due to the discreteness inherent to the selection and matching of sparse keypoints. We introduce DISK (DIScrete Keypoints), a novel method that overcomes these obstacles by leveragin ...

In this paper we derive convolutional filters for colour image whitening and decorrelation. Whilst whitening can be achieved via eigendecomposition of the image patch covariance, this operation is neither efficient nor biologically plausible. Given the shi ...

Most recent approaches to monocular non-rigid 3D shape recovery rely on exploiting point correspondences and work best when the whole surface is well-textured. The alternative is to rely either on contours or shading information, which has only been demons ...

State-of-the-art approaches for detecting filament-like structures in noisy images rely on filters optimized for signals of a particular shape, such as an ideal edge or ridge. While these approaches are optimal when the image conforms to these ideal shapes, their performance quickly degrades on many types of real data where the image deviates from the ideal model, and when noise processes violate a Gaussian assumption.

Tracking-by-detection has become the de facto standard approach to people tracking. To increase robustness, some approaches incorporate re-identification using appearance models and regressing motion offset, which requires costly identity annotations. In t ...

We propose a novel approach to reconstructing curvilinear tree structures evolving over time, such as road networks in 2D aerial images or neural structures in 3D microscopy stacks acquired in vivo. To enforce temporal consistency, we simultaneously proces ...

Self-supervised detection and segmentation of foreground objects aims for accuracy without annotated training data. However, existing approaches predominantly rely on restrictive assumptions on appearance and motion. For scenes with dynamic activities and ...

Accurate video-based ball tracking in team sports is important for automated game analysis, and has proven very difficult because the ball is often occluded by the players. In this paper, we propose a novel approach to addressing this issue by formulating ...

We propose an efficient approach to exploiting motion information from consecutive frames of a video sequence to recover the 3D pose of people. Previous approaches typically compute candidate poses in individual frames and then link them in a post-processi ...

This paper considers the task of finding a target location by making a limited number of sequential observations. Each observation results from evaluating an imperfect classifier of a chosen cost and accuracy on an interval of chosen length and position. W ...

(EN)A method for continuously tracking multiple people partitioned into groups while preserving identities under global appearance constraints, wherein people's trajectories may intersect, and wherein only sparse appearance information is available is disc ...

We present a real-time method for detecting deformable surfaces, with no need whatsoever for a priori pose knowledge. Our method starts from a set of wide baseline point matches between an undeformed image of the object and the image in which it is to be d ...

Pascal Fua

Chat with Graph Search

Learning Structured Models for Segmentation of 2D and 3D Imagery

Fast Keypoint Recognition in Ten Lines of Code

Simultaneous Segmentation and Anatomical Labeling of the Cerebral Vasculature

From Canonical Poses to 3D Motion Capture Using a Single Camera

Combining Geometric and Appearance Priors for Robust Homography Estimation

Fast Keypoint Recognition using Random Ferns

Local and global skeleton fitting techniques for optical motion capture

Closed-Form Solution to Non-rigid 3D Surface Registration

DISK: learning local features with policy gradient

Spatio-Chromatic Decorrelation by Shift-Invariant Filtering

Monocular 3D Reconstruction of Locally Textured Surfaces

Learning Rotational Features for Filament Detection

No Identity, no problem: Motion through detection for people tracking

Reconstructing Evolving Tree Structures in Time Lapse Sequences by Enforcing Time-Consistency

Human Detection and Segmentation via Multi-view Consensus

Take your Eyes off the Ball: Improving Ball-Tracking by Focusing on Team Play

Direct Prediction of 3D Body Poses from Motion Compensated Sequences

An Optimal Policy for Target Localization with Application to Electron Microscopy

Tracklet-based Multi-Commodity Network Flow for Tracking Multiple People

Real-Time Non-Rigid Surface Detection