Tome, D;
Peluse, P;
Agapito, L;
Badino, H;
(2019)
xR-EgoPose: Egocentric 3D Human Pose from an HMD Camera.
In:
2019 IEEE/CVF International Conference on Computer Vision (ICCV).
(pp. pp. 7727-7737).
IEEE: Seoul, Korea (South).
Preview |
Text
Tome_xR-EgoPose_Egocentric_3D_Human_Pose_From_an_HMD_Camera_ICCV_2019_paper.pdf - Published Version Download (1MB) | Preview |
Abstract
We present a new solution to egocentric 3D body pose estimation from monocular images captured from a downward looking fish-eye camera installed on the rim of a head mounted virtual reality device. This unusual viewpoint, just 2 cm away from the user's face, leads to images with unique visual appearance, characterized by severe self-occlusions and strong perspective distortions that result in a drastic difference in resolution between lower and upper body. Our contribution is two-fold. Firstly, we propose a new encoder-decoder architecture with a novel dual branch decoder designed specifically to account for the varying uncertainty in the 2D joint locations. Our quantitative evaluation, both on synthetic and real-world datasets, shows that our strategy leads to substantial improvements in accuracy over state of the art egocentric pose estimation approaches. Our second contribution is a new large-scale photorealistic synthetic dataset - xR-EgoPose - offering 383K frames of high quality renderings ofpeople with a diversity of skin tones, body shapes, clothing, in a variety of backgrounds and lighting conditions, performing a range of actions. Our experiments show that the high variability in our new synthetic training corpus leads to good generalization to real world footage and to state of the art results on real world datasets with ground truth. Moreover, an evaluation on the Human3.6M benchmark shows that the performance of our method is on par with top performing approaches on the more classic problem of 3D human pose from a third person viewpoint.
| Type: | Proceedings paper |
|---|---|
| Title: | xR-EgoPose: Egocentric 3D Human Pose from an HMD Camera |
| Event: | IEEE/CVF International Conference on Computer Vision (ICCV) |
| Location: | Seoul, SOUTH KOREA |
| Dates: | 27 October 2019 - 02 November 2019 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/ICCV.2019.00782 |
| Publisher version: | http://dx.doi.org/10.1109/ICCV.2019.00782 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Three-dimensional displays , Cameras, Pose estimation, Two dimensional displays, Training, Resists, Uncertainty |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10115309 |
Archive Staff Only
 |
View Item |
