Results 41 to 50 of about 129,382 (270)

2D–3D pose consistency-based conditional random fields for 3D human pose estimation [PDF]

open access: yesComputer Vision and Image Understanding, 2018
This study considers the 3D human pose estimation problem in a single RGB image by proposing a conditional random field (CRF) model over 2D poses, in which the 3D pose is obtained as a byproduct of the inference process. The unary term of the proposed CRF model is defined based on a powerful heat-map regression network, which has been proposed for 2D ...
Ju Yong Chang, Kyoung Mu Lee
openaire   +2 more sources

HTNet: Human Topology aware network for 3d Human pose estimation

open access: yesICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023
3D human pose estimation errors would propagate along the human body topology and accumulate at the end joints of limbs. Inspired by the backtracking mechanism in automatic control systems, we design an Intra-Part Constraint module that utilizes the parent nodes as the reference to build topological constraints for end joints at the part level. Further
Cai, Jialun   +5 more
openaire   +2 more sources

Motion Capture for Sporting Events Based on Graph Convolutional Neural Networks and Single Target Pose Estimation Algorithms

open access: yesApplied Sciences, 2023
Human pose estimation refers to accurately estimating the position of the human body from a single RGB image and detecting the location of the body. It serves as the basis for several computer vision tasks, such as human tracking, 3D reconstruction, and ...
Chengpeng Duan   +3 more
doaj   +1 more source

VIBE: Video Inference for Human Body Pose and Shape Estimation

open access: yes, 2020
Human motion is fundamental to understanding behavior. Despite progress on single-image 3D pose and shape estimation, existing video-based state-of-the-art methods fail to produce accurate and natural motion sequences due to a lack of ground-truth 3D ...
Athanasiou, Nikos   +2 more
core   +1 more source

Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image [PDF]

open access: yes, 2017
We propose a unified formulation for the problem of 3D human pose estimation from a single raw RGB image that reasons jointly about 2D joint estimation and 3D pose reconstruction to improve both tasks.
Agapito, Lourdes   +2 more
core   +2 more sources

Hybrid LSTM & Transformer for 3D Human Pose Estimation [PDF]

open access: yesITM Web of Conferences
3D human pose estimation (3DHPE) has evolved into a sophisticated and pivotal technique, emerging as a prominent research focus in computer vision and robotics, based on the power of deep neural networks.
Su Longjie
doaj   +1 more source

A Survey on Depth Ambiguity of 3D Human Pose Estimation

open access: yesApplied Sciences, 2022
Depth ambiguity is one of the main challenges of three-dimensional (3D) human pose estimation (HPE). The recent strategies of disambiguating have brought significant progress and remarkable breakthroughs in the field of 3D human pose estimation (3D HPE).
Siqi Zhang   +3 more
doaj   +1 more source

Cascaded 3D Full-body Pose Regression from Single Depth Image at 100 FPS

open access: yes, 2018
There are increasing real-time live applications in virtual reality, where it plays an important role in capturing and retargetting 3D human pose. But it is still challenging to estimate accurate 3D pose from consumer imaging devices such as depth camera.
Su, Le, Xia, Shihong, Zhang, Zihao
core   +1 more source

Forecasting Human Dynamics from Static Images

open access: yes, 2017
This paper presents the first study on forecasting human dynamics from static images. The problem is to input a single RGB image and generate a sequence of upcoming human body poses in 3D.
Chao, Yu-Wei   +4 more
core   +1 more source

Monocular 3D Human Pose Estimation by Classification [PDF]

open access: yes2011 IEEE International Conference on Multimedia and Expo, 2011
We present a novel approach to 2D and 3D human pose estimation in monocular images by building on and improving recent advances in this field. We take the full body pose as a combination of a 3D pose and a viewpoint and in this way define classes that are then learned by a classifier. Compared to part based approaches, our approach does not suffer from
Greif, Thomas   +2 more
openaire   +3 more sources

Home - About - Disclaimer - Privacy