Results 11 to 20 of about 129,382 (270)

A Survey of the State of the Art in Monocular 3D Human Pose Estimation: Methods, Benchmarks, and Challenges [PDF]

Sensors
Three-dimensional human pose estimation (3D HPE) from monocular RGB cameras is a fundamental yet challenging task in computer vision, forming the basis of a wide range of applications such as action recognition, metaverse, self-driving, and healthcare ...
Yan Guo, Tianhan Gao, Aoshuang Dong, Xinbei Jiang, Zichen Zhu, Fuxin Wang   +5 more
doaj   +2 more sources

Exploiting temporal information for 3D pose estimation [PDF]

, 2018
In this work, we address the problem of 3D human pose estimation from a sequence of 2D human poses. Although the recent success of deep networks has led many state-of-the-art methods for 3D pose estimation to train deep networks end-to-end to predict ...
Alejandro Newell, C Barron, C Ionescu, D Mehta, F Bogo, G Mori, HJ Lee, L Bo, L Sigal, S Hochreiter, S Li, S Park, V Ramakrishna, X Zhou, Y Du   +14 more
core   +2 more sources

Heuristic weakly supervised 3D human pose estimation

Computational Visual Media
Monocular 3D human pose estimation from RGB images has attracted significant attention in recent years. However, recent models depend on supervised training with 3D pose ground truth data or known pose priors for their target domains. 3D pose data is typically collected with motion capture devices, severely limiting their applicability.
Shuangjun Liu, Michael Wan, Sarah Ostadabbas   +2 more
doaj   +3 more sources

Adapted human pose: monocular 3D human pose estimation with zero real 3D pose data [PDF]

Applied Intelligence, 2022
The ultimate goal for an inference model is to be robust and functional in real life applications. However, training vs. test data domain gaps often negatively affect model performance. This issue is especially critical for the monocular 3D human pose estimation problem, in which 3D human data is often collected in a controlled lab setting.
Shuangjun Liu, Naveen Sehgal, Sarah Ostadabbas   +2 more
openaire   +2 more sources

EM-POSE: 3D Human Pose Estimation from Sparse Electromagnetic Trackers [PDF]

2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021
2021 IEEE/CVF International Conference on Computer Vision (ICCV)
Kaufmann, Manuel; id_orcid0000-0001-5309-319X, Zhao, Yi, Tang, Chengcheng, Tao, Lingling, Twigg, Christopher, Song, Jie, Wang, Robert Y., Hilliges, Otmar; id_orcid0000-0002-5068-3474   +7 more
openaire   +2 more sources

Estimation of 3D human pose using prior knowledge [PDF]

Journal of Electronic Imaging, 2021
Estimating three-dimensional human poses from the positions of two-dimensional joints has shown promising results.However, using two-dimensional joint coordinates as input loses more information than image-based approaches and results in ambiguity.In order to overcome this problem, we combine bone length and camera parameters with two-dimensional joint
Chen, Shu, Zhang, Lei, Zou, Beiji
openaire   +2 more sources

Scene-Aware Egocentric 3D Human Pose Estimation

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Egocentric 3D human pose estimation with a single head-mounted fisheye camera has recently attracted attention due to its numerous applications in virtual and augmented reality. Existing methods still struggle in challenging poses where the human body is highly occluded or is closely interacting with the scene. To address this issue, we propose a scene-
Wang, J., Luvizon, D., Xu, W., Liu, L., Sarkar, K., Theobalt, C. ; https://orcid.org/0000-0001-6104-6625   +5 more
openaire   +3 more sources

3D Human Pose Estimation = 2D Pose Estimation + Matching [PDF]

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
Demo code: https://github.com/flyawaychase ...
Chen, Ching-Hang, Ramanan, Deva
openaire   +2 more sources

View Invariant 3D Human Pose Estimation [PDF]

IEEE Transactions on Circuits and Systems for Video Technology, 2020
The recent success of deep networks has significantly advanced 3D human pose estimation from 2D images. The diversity of capturing viewpoints and the flexibility of the human poses, however, remain some significant challenges. In this paper, we propose a view invariant 3D human pose estimation module to alleviate the effects of viewpoint diversity. The
Guoqiang Wei, Cuiling Lan, Wenjun Zeng, Zhibo Chen   +3 more
openaire   +2 more sources

Reconstructing 3D human pose and shape from a single image and sparse IMUs [PDF]

PeerJ Computer Science, 2023
Background Model-based 3D pose estimation has been widely used in many 3D human motion analysis applications, in which vision-based and inertial-based are two distinct lines. Multi-view images in a vision-based markerless capture system provide essential
Xianhua Liao, Jiayan Zhuang, Ze Liu, Jiayan Dong, Kangkang Song, Jiangjian Xiao   +5 more
doaj   +2 more sources