V
Vlad Olaru
Researcher at Romanian Academy
Publications - 8
Citations - 2358
Vlad Olaru is an academic researcher from Romanian Academy. The author has contributed to research in topics: Body region & Motion capture. The author has an hindex of 4, co-authored 8 publications receiving 1642 citations.
Papers
More filters
Journal ArticleDOI
Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments
TL;DR: A new dataset, Human3.6M, of 3.6 Million accurate 3D Human poses, acquired by recording the performance of 5 female and 6 male subjects, under 4 different viewpoints, is introduced for training realistic human sensing systems and for evaluating the next generation of human pose estimation models and algorithms.
Proceedings ArticleDOI
3D Human Sensing, Action and Emotion Recognition in Robot Assisted Therapy of Children with Autism
TL;DR: How state-of-the-art 3d human pose reconstruction methods perform on the newly introduced action and emotion recognition tasks defined on non-staged videos, recorded during robot-assisted therapy sessions of children with autism are investigated.
Proceedings ArticleDOI
Three-Dimensional Reconstruction of Human Interactions
Mihai Fieraru,Mihai Zanfir,Elisabeta Oneata,Alin-Ionut Popa,Vlad Olaru,Cristian Sminchisescu +5 more
TL;DR: This paper introduces models for interaction signature estimation (ISP) encompassing contact detection, segmentation, and 3d contact signature prediction, and shows how such components can be leveraged in order to produce augmented losses that ensure contact consistency during 3d reconstruction.
Proceedings ArticleDOI
AIFit: Automatic 3D Human-Interpretable Feedback Models for Fitness Training
TL;DR: In this article, the authors introduce the first automatic system, AIFit, that performs 3D human sensing for fitness training, which can be used at home, outdoors, or at the gym.
Proceedings Article
Learning Complex 3D Human Self-Contact
Mihai Fieraru,Mihai Zanfir,Elisabeta Oneata,Alin-Ionut Popa,Vlad Olaru,Cristian Sminchisescu +5 more
TL;DR: In this paper, a model for self-contact prediction is proposed, which estimates the body surface signature of self contact, leveraging the localization of selfcontact in the image, during both training and inference.