Son stéréophonique | EPFL Graph Search

Le terme stéréophonie vient du grec stereo « spatial, solide » et phono « ton, le son ». Le son stéréophonique, plus communément appelé stéréo, est une méthode d'enregistrement et de reproduction sonore visant à reconstituer la répartition dans l'espace des sources d'origine. Ce relief sonore est habituellement obtenu à l'aide de deux canaux diffusés par au moins deux transducteurs (haut-parleurs ou écouteurs), eux-mêmes reliés à deux amplificateurs distincts. Dans des conditions idéales, l'auditeur perçoit les sons situés dans l'espace. Historique Le désir d'espace Clément Ader eut semble-t-il en premier l'idée d'une diffusion stéréo, en 1881. En 1884, sept ans seulement après l'invention du téléphone, le théatrophone permet alors à des auditeurs d'écouter, avec un écouteur par oreille et un micro par écouteur, la musique jouée à l'Opéra Garnier, à Paris, depuis un bâtiment voisin. Le terme stéréophonie apparaît en France en 1924. , écrit en 1930 l'ingénieu

Structure-aware Multi-view 3D Reconstruction of Dislocations in TEM with Message Passing Neural Networks

Okan Altingövde, Pascal Fua, Gulnaz Ganeeva, Cécile Hébert, Anastasiia Mishchuk, Emadeddin Oveisi

Efficient analysis of the three-dimensional (3D) shape and distribution of curvilinear crystal defects, namely dislocations, is an open research topic in material science and computer vision. In order to determine the structural and opto-electrical characteristics of the material, accurate 3D reconstructions of dislocations are required. In its current state, an established way to obtain 3D information of dislocations is electron tomography which relies on acquiring dozens of images from tilted sample for wide range of angles. Although tomography yields sufficient results in many cases, it is manually demanding to acquire, register and process dozens of images. In previous works [1, 2], it is shown that a classical stereo reconstruction approach may be applied as an alternative in order to increase reconstruction throughput while providing good performance. A later work [3] employing modern data-driven computer vision models showed that this stereo approach can be largely automatized and be used in various imaging conditions. In this work, we further improve the performance and memory consumption of previous convolutional neural network (CNN) based stereo reconstruction approach and extend it to be applicable in cases where more than two images are available. Our proposed multi-view approach directly incorporates the structural prior of dislocations to the model"s architecture and estimates 3D line segments approximating 3D shape of dislocations. In its core, our method has two stages which are structural connectivity estimation and depth estimation. In first stage, we employ a CNN to estimate affinity of sampled image locations on dislocation cores. This affinity information is used in the later depth estimation stage to eliminate the depth discontinuities on dislocations (Figure1). Unlike previous deep data-driven method, our new approach uses structural knowledge to separate depth estimations of different dislocation segments and yields more accurate reconstructions. In Figure 2, an example affinity estimation is shown for 4 different image locations on the same dislocation. It may be seen that dislocation points that are connected by dislocation segment in 3D results in higher affinity. This information is crucial to connect 3D point estimations and obtain linear structures in 3D.

2021

MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation

Alexandre Massoud Alahi, Lorenzo Bertoni, Sven Kreiss

We tackle the fundamentally ill-posed problem of 3D human localization from monocular RGB images. Driven by the limitation of neural networks outputting point estimates, we address the ambiguity in the task by predicting confidence intervals through a loss function based on the Laplace distribution. Our architecture is a light-weight feed-forward neural network that predicts 3D locations and corresponding confidence intervals given 2D human poses. The design is particularly well suited for small training data, cross-dataset generalization, and real-time applications. Our experiments show that we (i) outperform state-of-the-art results on KITTI and nuScenes datasets, (ii) even outperform a stereo-based method for far-away pedestrians, and (iii) estimate meaningful confidence intervals. We further share insights on our model of uncertainty in cases of limited observations and out-of-distribution samples.

2019

Structure-aware Multi-view 3D Reconstruction of Dislocations in TEM with Message Passing Neural Networks

Okan Altingövde, Pascal Fua, Gulnaz Ganeeva, Cécile Hébert, Anastasiia Mishchuk, Emadeddin Oveisi

2021