Handoccnet: Occlusion-robust 3d hand mesh estimation network

JK Park, Y Oh, G Moon, H Choi… - Proceedings of the …, 2022 - openaccess.thecvf.com
Hands are often severely occluded by objects, which makes 3D hand mesh estimation
challenging. Previous works often have disregarded information at occluded regions …

A2j: Anchor-to-joint regression network for 3d articulated pose estimation from a single depth image

F Xiong, B Zhang, Y Xiao, Z Cao, T Yu… - Proceedings of the …, 2019 - openaccess.thecvf.com
For 3D hand and body pose estimation task in depth image, a novel anchor-based approach
termed Anchor-to-Joint regression network (A2J) with the end-to-end learning ability is …

Dense 3d regression for hand pose estimation

C Wan, T Probst, L Van Gool… - Proceedings of the IEEE …, 2018 - openaccess.thecvf.com
We present a simple and effective method for 3D hand pose estimation from a single depth
frame. As opposed to previous state-of-arts based on holistic 3D regression, our method …

3d human pose estimation in rgbd images for robotic task learning

C Zimmermann, T Welschehold… - … on Robotics and …, 2018 - ieeexplore.ieee.org
We propose an approach to estimate 3D human pose in real world units from a single RGBD
image and show that it exceeds performance of monocular 3D pose estimation approaches …

HandGCNFormer: a novel topology-aware transformer network for 3d hand pose estimation

Y Wang, LL Chen, J Li, X Zhang - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Despite the substantial progress in 3D hand pose estimation, inferring plausible and
accurate poses in the presence of severe self-occlusion and high self-similarity remains an …

Unsupervised domain adaptation for 3D human pose estimation

X Zhang, Y Wong, MS Kankanhalli… - Proceedings of the 27th …, 2019 - dl.acm.org
Training an accurate 3D human pose estimator often requires a large amount of 3D ground-
truth data which is inefficient and costly to collect. Previous methods have either resorted to …

Self-calibrated multi-sensor wearable for hand tracking and modeling

N Gosala, F Wang, Z Cui, H Liang… - … on Visualization and …, 2021 - ieeexplore.ieee.org
We present a multi-sensor system for consistent 3D hand pose tracking and modeling that
leverages the advantages of both wearable and optical sensors. Specifically, we employ a …

[HTML][HTML] An Efficient Motion Adjustment Method for a Dual-Arm Transfer Robot Based on a Two-Level Neural Network and a Greedy Algorithm

M Chen, Q Liu, K Wang, Z Yang, S Guo - Electronics, 2024 - mdpi.com
As the manipulation object of a patient transfer robot is a human, which can be considered a
complex and time-varying system, motion adjustment of a patient transfer robot is inevitable …

Multi-person 3D pose estimation from 3D cloud data using 3D convolutional neural networks

M Vasileiadis, CS Bouganis, D Tzovaras - Computer Vision and Image …, 2019 - Elsevier
Human pose estimation is considered one of the major challenges in the field of Computer
Vision, playing an integral role in a large variety of technology domains. While, in the last …

3D hand pose and mesh estimation via a generic Topology-aware Transformer model

S Yu, Y Wang, L Chen, X Zhang, J Li - Frontiers in Neurorobotics, 2024 - frontiersin.org
In Human-Robot Interaction (HRI), accurate 3D hand pose and mesh estimation hold critical
importance. However, inferring reasonable and accurate poses in severe self-occlusion and …