Deep kinematic pose regression

X Zhou, X Sun, W Zhang, S Liang, Y Wei - … , October 8-10 and 15-16, 2016 …, 2016 - Springer
kinematic object model into the deep neutral network learning for general articulated object
pose … we show that integrating a kinematic object model into deep learning achieves state-of-…

Deep kinematics analysis for monocular 3d human pose estimation

J Xu, Z Yu, B Ni, J Yang, X Yang… - Proceedings of the …, 2020 - openaccess.thecvf.com
… In this paper, we propose a deep kinematics analysis framework for monocular 3D pose
estimation. By explicitly incorporating kinematics regularization into deep models, we achieves …

Repose: Learning deep kinematic priors for fast human pose estimation

H Isack, C Haene, C Keskin, S Bouaziz… - arXiv preprint arXiv …, 2020 - arxiv.org
We propose a novel efficient and lightweight model for human pose estimation from a single
image. Our model is designed to achieve competitive results at a fraction of the number of …

[HTML][HTML] Gaussian process regression for forward and inverse kinematics of a soft robotic arm

C Relaño, J Muñoz, CA Monje - Engineering Applications of Artificial …, 2023 - Elsevier
… to produce a motion, while kinematics focuses only on the … kinematics, which determines
the final position of the robot end as a function of the given inputs, and the inverse kinematics, …

Kinematic pose rectification for performance analysis and retrieval in sports

D Zecha, M Einfalt, C Eggert… - Proceedings of the …, 2018 - openaccess.thecvf.com
… of deep learning enable the measurement of kinematic coefficients directly from human pose
… swimming pool by means of a deep neural network architecture for key-pose regression. [24…

Improve regression network on depth hand pose estimation with auxiliary variable

L Xu, C Hu, J Xue, K Mei - … on Circuits and Systems for Video …, 2020 - ieeexplore.ieee.org
… Compared with previous hand pose regression methods that define the kinematics
structure explicitly [4], [17], our method learns the underlying pattern implicitly by learning the …

A kinematic bottleneck approach for pose regression of flexible surgical instruments directly from images

L Sestini, B Rosa, E De Momi… - IEEE Robotics and …, 2021 - ieeexplore.ieee.org
… In this work, we propose a method for 3-D pose estimation of flexible surgical instruments.
The proposed approach is self-supervised and trains a model to regress the kinematic

Simple and effective deep hand shape and pose regression from a single depth image

J Malik, A Elhayek, F Nunnari, D Stricker - Computers & Graphics, 2019 - Elsevier
… Overview of our approach for hand shape and pose regression. A depth input (I D ) is given
to the convolutional neural network (CNN), which provides a feature map for four distinct …

Dense 3d regression for hand pose estimation

C Wan, T Probst, L Van Gool… - Proceedings of the IEEE …, 2018 - openaccess.thecvf.com
regression method for hand poseregression of 2D joint detections helps 3D regression
and how different strategies to fuse 2D joint detections and 3D regressions impact the final pose

Cascaded 3d full-body pose regression from single depth image at 100 fps

S Xia, Z Zhang, L Su - 2018 IEEE Conference on Virtual Reality …, 2018 - ieeexplore.ieee.org
pose regression method [22] and feature points regression of human face [6], in this paper,
we assume that the more regression/… have, the more accurate human pose we can get. This …