2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020
DOI: 10.1109/cvpr42600.2020.00704
|View full text |Cite
|
Sign up to set email alerts
|

Optical Non-Line-of-Sight Physics-Based 3D Human Pose Estimation

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
28
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
5
4
1

Relationship

3
7

Authors

Journals

citations
Cited by 59 publications
(28 citation statements)
references
References 29 publications
0
28
0
Order By: Relevance
“…Other sensors/sources: Besides using the aforementioned sensors, Isogawa et al [237] estimated 3D human pose from the 3D spatio-temporal histogram of photons captured by a non-line-of-sight (NLOS) imaging system. Tome et al [238] tackled the egocentric 3D pose estimation via a fish-eye camera.…”
Section: D Hpe From Other Sourcesmentioning
confidence: 99%
“…Other sensors/sources: Besides using the aforementioned sensors, Isogawa et al [237] estimated 3D human pose from the 3D spatio-temporal histogram of photons captured by a non-line-of-sight (NLOS) imaging system. Tome et al [238] tackled the egocentric 3D pose estimation via a fish-eye camera.…”
Section: D Hpe From Other Sourcesmentioning
confidence: 99%
“…At present, NLOS has been used in human pose classification through scattering media [115], three-dimensional multihuman pose estimation [116] and movement-based object tracking [117].…”
Section: F Non-line-of-sight Imagingmentioning
confidence: 99%
“…Our approach addresses these drawbacks with a framework that integrates kinematic inference with RL-based character control, which runs in real-time, is compatible with advanced physics simulators, and has learning mechanisms that aim to match the output motion to the ground truth. Although prior work [64,65,16] has used RL to produce simple human locomotions from videos, these methods only learn policies that coarsely mimic limited types of motion instead of precisely tracking the motion presented in the video. In contrast, our approach can achieve accurate pose estimation by integrating images-based kinematic inference and RL-based character control with the proposed policy design and meta-PD control.…”
Section: Related Workmentioning
confidence: 99%