Publication
3D Reconstruction of Optical Diffraction Tomography Based on a Neural Network Model
Publications associées (121)
Learning Lipschitz-Controlled Activation Functions in Neural Networks for Plug-and-Play Image Reconstruction Methods
Michaël Unser, Dimitris Perdios, Pakshal Narendra Bohra, Alexis Marie Frederic Goujon, Sébastien Alexandre Emery
Ill-posed linear inverse problems are frequently encountered in image reconstruction tasks. Image reconstruction methods that combine the Plug-and-Play (PnP) priors framework with convolutional neural network (CNN) based denoisers have shown impressive per ...
2021Perceiving Humans: from Monocular 3D Localization to Social Distancing
Alexandre Massoud Alahi, Sven Kreiss, Lorenzo Bertoni
Perceiving humans in the context of Intelligent Transportation Systems (ITS) often relies on multiple cameras or expensive LiDAR sensors. In this work, we present a new cost-effective vision-based method that perceives humans' locations in 3D and their bod ...
2021Polarization-sensitive optics diffraction tomography
Demetri Psaltis, Joowon Lim, Elizabeth Elena Antoine, Amirhossein Saba Shirvan, Ahmed Ayoub
Polarization of light has been widely used as a contrast mechanism in two-dimensional (2D) microscopy and also in some three-dimensional (3D) imaging modalities. In this paper, we report the 3D tomographic reconstruction of the refractive index (RI) tensor ...
OPTICAL SOC AMER2021Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlases
Pascal Fua, Mathieu Salzmann, Shaifali Parashar, Jan Bednarík, Siddhartha Chaudhuri
We propose a method for the unsupervised reconstruction of a temporally-coherent sequence of surfaces from a sequence of time-evolving point clouds, yielding dense, semantically meaningful correspondences between all keyframes. We represent the reconstruct ...
20213D reconstruction of weakly scattering objects from 2D intensity-only measurements using the Wolf transform
Demetri Psaltis, Joowon Lim, Elizabeth Elena Antoine, Ahmed Ayoub
A new approach to optical diffraction tomography (ODT) based on intensity measurements is presented. By applying the Wolf transform directly to intensity measurements, we observed unexpected behavior in the 3D reconstruction of the sample. Such a reconstru ...
OPTICAL SOC AMER2021How to teach neural networks to mesh: Application on 2-D simplicial contours
François Avellan, Pascal Clausen, Alexis Papagiannopoulos
A machine learning meshing scheme for the generation of 2-D simplicial meshes is proposed based on the predictions of neural networks. The data extracted from meshed contours are utilized to train neural networks which are used to approximate the number of ...
2021Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search
Weight sharing has become a de facto standard in neural architecture search because it enables the search to be done on commodity hardware. However, recent works have empirically shown a ranking disorder between the performance of stand-alone architectures ...
IEEE COMPUTER SOC2021Continual Learning for Natural Language Generation in Task-oriented Dialog Systems
Boi Faltings, Mengjie Zhao, Fei Mi, Liangwei Chen
Natural language generation (NLG) is an essential component of task-oriented dialog systems. Despite the recent success of neural approaches for NLG, they are typically developed in an offline manner for particular domains. To better fit real-life applicat ...
2021Wasserstein Adversarial Regularization for learning with label noise
Devis Tuia, Sylvain Lobry, Nicolas Courty
Noisy labels often occur in vision datasets, especially when they are obtained from crowdsourcing or Web scraping. We propose a new regularization method, which enables learning robust classifiers in presence of noisy data. To achieve this goal, we propose ...
2021Learning approaches to high-fidelity optical diffraction tomography
Optical diffraction tomography (ODT) provides us 3D refractive index (RI) distributions of transparent samples. Since RI values differ across different materials, they serve as endogenous contrasts. It, therefore, enables us to image without pre-processing ...
EPFL2020