M
Marie-Odile Berger
Researcher at French Institute for Research in Computer Science and Automation
Publications - 118
Citations - 2238
Marie-Odile Berger is an academic researcher from French Institute for Research in Computer Science and Automation. The author has contributed to research in topics: Augmented reality & Pose. The author has an hindex of 24, co-authored 111 publications receiving 2077 citations. Previous affiliations of Marie-Odile Berger include General Electric & Centre national de la recherche scientifique.
Papers
More filters
Proceedings ArticleDOI
3D-Aware Ellipse Prediction for Object-Based Camera Pose Estimation
TL;DR: In this paper, a learning-based method is proposed to detect improved elliptic approximations of objects which are coherent with the 3D ellipsoid in terms of perspective projection.
Proceedings Article
Active models for regularizing formant trajectories.
Yves Laprie,Marie-Odile Berger +1 more
Towards a True Acoustic-Visual Speech Synthesis
Asterios Toutios,Utpala Musti,Slim Ouni,Vincent Colotte,Brigitte Wrobel-Dautcourt,Marie-Odile Berger +5 more
TL;DR: Results indicate the benefits of this approach, since both the synthesized speech signal and the face animation are of good quality, and the proposed method addresses the problems of asyn- chrony and incoherence inherent in classic approaches to audiovisual synthesis.
Proceedings ArticleDOI
Viewpoint simulation for camera pose estimation from an unstructured scene model
TL;DR: Viewpoint simulation permits pose estimation in situations where the approach based on the sole SIFT descriptors simply fails, and can enrich a scene model by adding descriptors from simulated views, using either orthographic or pinhole virtual cameras.
Proceedings Article
Intra- and intre-observer variability in the angiographic delineation of brain arterio-venous malformations.
TL;DR: The purpose of this study is to determine the intra- and inter-observer variability in the manual delineation of the boundaries of brain arterio-venous malformations (AVMs) on digital subtracted angiograms to define the target volume in stereotactic radiotherapy.