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.

In earlier work, we proposed treating wide baseline matching of feature points as a classification problem, in which each class corresponds to the set of all possible views of such a point. We used a K-mean plus Nearest Neighbor classifier to validate our approach, mostly because it was simple to implement. It has proved effective but still too slow for real-time use. In this paper, we advocate instead the use of randomized trees as the classification technique. It is both fast enough for real-time performa

This paper presents the first photometric registration pipeline for Mixed Reality based on high quality illumination estimation by convolutional neural network (CNN) methods. For easy adaptation and deployment of the system, we train the CNN using purely s ...

Deep learning has revolutionalized image-level tasks such as classification, but patch-level tasks, such as correspondence, still rely on hand-crafted features, e.g. SIFT. In this paper we use Convolutional Neural Networks (CNNs) to learn discriminant patc ...

The shape is commonly used to describe the objects. State-of-the-art algorithms in medical imaging are predominantly diverging from computer vision, where voxel grids, meshes, point clouds, and implicit surface models are used. This is seen from the growin ...

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 ...

Optical motion capture provides an impressive ability to replicate gestures. However, even with a highly professional system there are many instances where crucial markers are occluded or when the algorithm confuses the trajectory of one marker with that of another. This requires much editing work on the part of the animator before the virtual characters are ready for their screen debuts. In this paper, we present an approach to increasing the robustness of a motion capture system by using a sophisticated a

Finding the centerline and estimating the radius of linear structures is a critical first step in many applications, ranging from road delineation in 2D aerial images to modeling blood vessels, lung bronchi, and dendritic arbors in 3D biomedical image stac ...

Deriving accurate three-dimensional (3-D) structural information of materials at the nanometre level is often crucial for understanding their properties. Tomography in transmission electron microscopy (TEM) is a powerful technique that provides such inform ...

Synthetic modeling of human bodies and the simulation of motion is a long-standing problem in animation and much work is involved before a near-realistic performance can be achieved. At present, it takes an experienced designer a very long time to build a complete and realistic model that closely resembles a specific person. Our ultimate goal is to automate the process and to produce realistic animation models given a set of video sequences. In this paper we show that, given video sequences of a person movi

A generalized expectation maximization (GEM) algorithm is used to retrieve the pose of a person from a monocular video sequence shot with a moving camera. After embedding the set of possible poses in a low dimensional space using principal component analys ...

Occlusions remain one of the key challenges in 3D body pose estimation from single-camera video sequences. Temporal consistency has been extensively used to mitigate their impact but the existing algorithms in the literature do not explicitly model them.Here, we apply this by representing the deforming body as a spatio-temporal graph. We then introduce a refinement network that performs graph convolutions over this graph to output 3D poses. To ensure robustness to occlusions, we train this network with a se

We propose a novel approach to automatically detecting and tracking cell populations in time-lapse images. Unlike earlier ones that rely on linking a predetermined and potentially under-complete set of detections, we generate an overcomplete set of competing detection hypotheses. We then perform detection and tracking simultaneously by solving an integer program to find an optimal and consistent subset. This eliminates the need for heuristics to handle missed detections due to occlusions and complex morphol

Prominent feature point descriptors such as SIFT and SURF allow reliable real-time matching but at a computational cost that limits the number of points that can be handled on PCs, and even more on less powerful mobile devices. A recently proposed technique that relies on statistical classification to compute signatures has the potential to be much faster but at the cost of using very large amounts of memory, which makes it impractical for implementation on low-memory devices.

Statistical learning techniques have been used to dramatically speed-up keypoint matching by training a classifier to recognize a specific set of keypoints. However, the training itself is usually relatively slow and performed offline. Although methods hav ...

Most state-of-the-art algorithms for filament detection in 3-D image-stacks rely on computing the Hessian matrix around individual pixels and labeling these pixels according to its eigenvalues. This approach, while very effective for clean data, hi which linear structures are nearly cylindrical, loses its effectiveness in the presence of noisy data and irregular structures.

We present a novel approach to fully automated reconstruction of tree structures in noisy 2D images. Unlike in earlier approaches, we explicitly handle crossovers and bifurcation points, and impose geometric constraints while optimizing a global cost funct ...

Studying how neural circuits orchestrate limbed behaviors requires the precise measurement of the positions of each appendage in 3-dimensional (3D) space. Deep neural networks can estimate 2-dimensional (2D) pose in freely behaving and tethered animals. Ho ...

Re-identification is usually defined as the problem of deciding whether a person currently in the field of view of a camera has been seen earlier either by that camera or another. However, a different version of the problem arises even when people are seen by multiple cameras with overlapping fields of view. Current tracking algorithms can easily get confused when people come close to each other and merge trajectory fragments into trajectories that include erroneous identity switches. Preventing this means

We present a method for segmenting cracks in images of masonry buildings damaged by earthquakes. Existing methods of crack detection fail to preserve the continuity of cracks, and their performance deteriorates with imprecise training labels. We address th ...

Recent approaches to drape garments quickly over arbitrary human bodies leverage self-supervision to eliminate the need for large training sets. However, they are designed to train one network per clothing item, which severely limits their generalization a ...

Pascal Fua

Chat with Graph Search

Randomized Trees for Real-Time Keypoint Recognition

Learning Lightprobes for Mixed Reality Illumination

Discriminative Learning of Deep Convolutional Feature Point Descriptors

MedShapeNet - a large-scale dataset of 3D medical shapes for computer vision

Implicit Meshes for Surface Reconstruction

Skeleton-based motion capture for robust reconstruction of human motion

Multiscale Centerline Detection

Stereo-vision three-dimensional reconstruction of curvilinear structures imaged with a TEM

Automated body modeling from video sequences

Tracking Articulated Bodies using Generalized Expectation Maximization

Occlusion Resilient 3D Human Pose Estimation

Detecting and Tracking Cells using Network Flow Programming

Compact Signatures for High-speed Interest Point Description and Matching

Keypoint Signatures for Fast Learning and Recognition

Steerable Features for Statistical 3D Dendrite Detection

Reconstructing Geometrically Consistent Tree Structures from Noisy Images

DeepFly3D, a deep learning-based approach for 3D limb and appendage tracking in tethered, adult Drosophila

Re-Identification for Improved People Tracking

TOPO-Loss for continuity-preserving crack detection using deep learning

DrapeNet: Garment Generation and Self-Supervised Draping