User profiles for Pascal Fua
Pascal FuaProfessor Computer Science, EPFL Verified email at epfl.ch Cited by 76189 |
SLIC superpixels compared to state-of-the-art superpixel methods
Computer vision applications have come to rely increasingly on superpixels in recent years,
but it is not always clear what constitutes a good superpixel algorithm. In an effort to …
but it is not always clear what constitutes a good superpixel algorithm. In an effort to …
Context-aware crowd counting
State-of-the-art methods for counting people in crowded scenes rely on deep networks to
estimate crowd density. They typically use the same filters over the whole image or over large …
estimate crowd density. They typically use the same filters over the whole image or over large …
Brief: Binary robust independent elementary features
We propose to use binary strings as an efficient feature point descriptor, which we call
BRIEF.We show that it is highly discriminative even when using relatively few bits and can be …
BRIEF.We show that it is highly discriminative even when using relatively few bits and can be …
EPnP: An Accurate O(n) Solution to the PnP Problem
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 …
calibrated camera from n 3D-to-2D point correspondences—whose computational complexity …
Slic superpixels
Superpixels are becoming increasingly popular for use in computer vision applications.
However, there are few algorithms that output a desired number of regular, compact superpixels …
However, there are few algorithms that output a desired number of regular, compact superpixels …
Lift: Learned invariant feature transform
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 …
pipeline, that is, detection, orientation estimation, and feature description. While previous …
Keypoint recognition using randomized trees
In many 3D object-detection and pose-estimation problems, runtime performance is of critical
importance. However, there usually is time to train the system, which we would show to be …
importance. However, there usually is time to train the system, which we would show to be …
Fast keypoint recognition using random ferns
While feature point recognition is a key component of modern approaches to object detection,
existing approaches require computationally expensive patch preprocessing to handle …
existing approaches require computationally expensive patch preprocessing to handle …
Randomized trees for real-time keypoint recognition
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…
problem, in which each class corresponds to the set of all possible views of such a point…
Daisy: An efficient dense descriptor applied to wide-baseline stereo
In this paper, we introduce a local image descriptor, DAISY, which is very efficient to compute
densely. We also present an EM-based algorithm to compute dense depth and occlusion …
densely. We also present an EM-based algorithm to compute dense depth and occlusion …