Reference : Towards Generalization of 3D Human Pose Estimation In The Wild |
Scientific congresses, symposiums and conference proceedings : Paper published in a book | |||
Engineering, computing & technology : Computer science | |||
http://hdl.handle.net/10993/44700 | |||
Towards Generalization of 3D Human Pose Estimation In The Wild | |
English | |
Baptista, Renato ![]() | |
Saint, Alexandre Fabian A ![]() | |
Al Ismaeil, Kassem ![]() | |
Aouada, Djamila ![]() | |
2020 | |
International Conference on Pattern Recognition (ICPR) Workshop on 3D Human Understanding, Milan 10-15 January 2021 | |
Yes | |
International | |
International Conference on Pattern Recognition (ICPR) Workshop on 3D Human Understanding | |
10-15 January 2021 | |
[en] 3D human pose estimation ; 3DBodyTex.Pose ; synthetic data ; in-the-wild | |
[en] In this paper, we propose 3DBodyTex.Pose, a dataset that addresses the task of 3D human pose estimation in-the-wild. Generalization to in-the-wild images remains limited due to the lack of adequate datasets. Existent ones are usually collected in indoor controlled environments where motion capture systems are used to obtain the 3D ground-truth annotations of humans.
3DBodyTex.Pose offers high quality and rich data containing 405 different real subjects in various clothing and poses, and 81k image samples with ground-truth 2D and 3D pose annotations. These images are generated from 200 viewpoints among which 70 challenging extreme viewpoints. This data was created starting from high resolution textured 3D body scans and by incorporating various realistic backgrounds. Retraining a state-of-the-art 3D pose estimation approach using data augmented with 3DBodyTex.Pose showed promising improvement in the overall performance, and a sensible decrease in the per joint position error when testing on challenging viewpoints. The 3DBodyTex.Pose is expected to offer the research community with new possibilities for generalizing 3D pose estimation from monocular in-the-wild images. | |
Researchers | |
http://hdl.handle.net/10993/44700 | |
FnR ; FNR10415355 > Bjorn Ottersten > 3D-ACT > 3D Action Recognition Using Refinement and Invariance Strategies for Reliable Surveillance > 01/06/2016 > 31/05/2019 > 2015 |
File(s) associated to this reference | ||||||||||||||
Fulltext file(s):
| ||||||||||||||
All documents in ORBilu are protected by a user license.