Publications related to Tracing in 2D to reduce the annotation effort for 3D deep delineation of linear structures

Shape Reconstruction by Learning Differentiable Surface Representations

Pascal Fua, Mathieu Salzmann, Shaifali Parashar, Jan Bednarík, Erhan Gündogdu

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 ...

2020

Square Attack: a query-efficient black-box adversarial attack via random search

Nicolas Henri Bernard Flammarion, Maksym Andriushchenko, Francesco Croce

We propose the Square Attack, a new score-based black-box

l_2

and

l_\infty

adversarial attack that does not rely on local gradient information and thus is not affected by gradient masking. The Square Attack is based on a randomized search scheme where ...

2020

Neural Scene Decomposition for Multi-Person Motion Capture

Pascal Fua, Mathieu Salzmann, Isinsu Katircioglu, Helge Jochen Rhodin, Victor Constantin

Learning general image representations has proven key to the success of many computer vision tasks. For example, many approaches to image understanding problems rely on deep networks that were initially trained on ImageNet, mostly because the learned featu ...

IEEE2019

GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Draping

Pascal Fua, Mathieu Salzmann, Victor Constantin, Erhan Gündogdu

While Physics-Based Simulation (PBS) can accurately drape a 3D garment on a 3D body, it remains too costly for real-time applications, such as virtual try-on. By contrast, inference in a deep network, requiring a single forward pass, is much faster. Taking ...

IEEE2019

Optical projection tomography for whole organ imaging

David Nguyen

In the past twenty years, far-reaching studies of molecular and cellular processes have reached a milestone in their maturation, and the knowledge from these studies was ready to apply at higher organizational levels. At that time, rodent models were long ...

EPFL2019

Mirror, Mirror, on the Wall, Who’s Got the Clearest Image of Them All?—A Tailored Approach to Single Image Reflection Removal

Sabine Süsstrunk, Georg Maierhofer

Removing reflection artefacts from a single image is a problem of both theoretical and practical interest, which still presents challenges because of the massively ill-posed nature of the problem. In this paper, we propose a technique based on a novel opti ...

2019

Evaluation of Deep Learning Strategies for Nucleus Segmentation in Fluorescence Images

Matthieu Jean-Michel Philippe Broisin, Jonathan Roth

Identifying nuclei is often a critical first step in analyzing microscopy images of cells and classical image processing algorithms are most commonly used for this task. Recent developments in deep learning can yield superior accuracy, but typical evaluati ...

WILEY2019

Geometric and Physical Constraints for Drone-Based Head Plane Crowd Density Estimation

Pascal Fua, Mathieu Salzmann, Weizhe Liu, Krzysztof Maciej Lis

State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density in the image plane. While useful for this purpose, this image- plane density has no immediate physical meaning because it is subject to perspecti ...

IEEE2019

Robustness of Classifiers to Universal Perturbations: A Geometric Perspective

Pascal Frossard, Seyed Mohsen Moosavi Dezfooli, Alhussein Fawzi

Deep networks have recently been shown to be vulnerable to universal perturbations: there exist very small image-agnostic perturbations that cause most natural images to be misclassified by such classifiers. In this paper, we provide a quantitative analysi ...

2018

Deep(ly) Learning the Depth

Xun Victor Suo

We report on the use of deep learning algorithms to perform depth recovery in multiview imaging. We show that if enough training data are provided, a neural network such as multilayer perceptron can be trained to recover the depth in multiview imaging as a ...

2016

Tracing in 2D to reduce the annotation effort for 3D deep delineation of linear structures

Graph Chatbot

Chat with Graph Search

Shape Reconstruction by Learning Differentiable Surface Representations

Square Attack: a query-efficient black-box adversarial attack via random search

Neural Scene Decomposition for Multi-Person Motion Capture

GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Draping

Optical projection tomography for whole organ imaging

Mirror, Mirror, on the Wall, Who’s Got the Clearest Image of Them All?—A Tailored Approach to Single Image Reflection Removal

Evaluation of Deep Learning Strategies for Nucleus Segmentation in Fluorescence Images

Geometric and Physical Constraints for Drone-Based Head Plane Crowd Density Estimation

Robustness of Classifiers to Universal Perturbations: A Geometric Perspective

Deep(ly) Learning the Depth

Shape Reconstruction by Learning Differentiable Surface Representations

Geometric and Physical Constraints for Drone-Based Head Plane Crowd Density Estimation

Square Attack: a query-efficient black-box adversarial attack via random search

Neural Scene Decomposition for Multi-Person Motion Capture

GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Draping

Optical projection tomography for whole organ imaging

Deep(ly) Learning the Depth

Mirror, Mirror, on the Wall, Who’s Got the Clearest Image of Them All?—A Tailored Approach to Single Image Reflection Removal

Evaluation of Deep Learning Strategies for Nucleus Segmentation in Fluorescence Images

Robustness of Classifiers to Universal Perturbations: A Geometric Perspective