[HTML][HTML] Deep 3D human pose estimation: A review

J Wang, S Tan, X Zhen, S Xu, F Zheng, Z He… - Computer Vision and …, 2021‏ - Elsevier
Abstract Three-dimensional (3D) human pose estimation involves estimating the articulated
3D joint locations of a human body from an image or video. Due to its widespread …

Deep learning-based human pose estimation: A survey

C Zheng, W Wu, C Chen, T Yang, S Zhu, J Shen… - ACM Computing …, 2023‏ - dl.acm.org
Human pose estimation aims to locate the human body parts and build human body
representation (eg, body skeleton) from input data such as images and videos. It has drawn …

Bedlam: A synthetic dataset of bodies exhibiting detailed lifelike animated motion

MJ Black, P Patel, J Tesch… - Proceedings of the IEEE …, 2023‏ - openaccess.thecvf.com
We show, for the first time, that neural networks trained only on synthetic data achieve state-
of-the-art accuracy on the problem of 3D human pose and shape (HPS) estimation from real …

Human motion diffusion as a generative prior

Y Shafir, G Tevet, R Kapon, AH Bermano - arxiv preprint arxiv:2303.01418, 2023‏ - arxiv.org
Recent work has demonstrated the significant potential of denoising diffusion models for
generating human motion, including text-to-motion capabilities. However, these methods are …

Smpler-x: Scaling up expressive human pose and shape estimation

Z Cai, W Yin, A Zeng, C Wei, Q Sun… - Advances in …, 2023‏ - proceedings.neurips.cc
Expressive human pose and shape estimation (EHPS) unifies body, hands, and face motion
capture with numerous applications. Despite encouraging progress, current state-of-the-art …

End-to-end human pose and mesh reconstruction with transformers

K Lin, L Wang, Z Liu - … of the IEEE/CVF conference on …, 2021‏ - openaccess.thecvf.com
We present a new method, called MEsh TRansfOrmer (METRO), to reconstruct 3D human
pose and mesh vertices from a single image. Our method uses a transformer encoder to …

Mesh graphormer

K Lin, L Wang, Z Liu - Proceedings of the IEEE/CVF …, 2021‏ - openaccess.thecvf.com
We present a graph-convolution-reinforced transformer, named Mesh Graphormer, for 3D
human pose and mesh reconstruction from a single image. Recently both transformers and …

Cross-attention of disentangled modalities for 3d human mesh recovery with transformers

J Cho, K Youwang, TH Oh - European Conference on Computer Vision, 2022‏ - Springer
Transformer encoder architectures have recently achieved state-of-the-art results on
monocular 3D human mesh reconstruction, but they require a substantial number of …

Hybrik: A hybrid analytical-neural inverse kinematics solution for 3d human pose and shape estimation

J Li, C Xu, Z Chen, S Bian… - Proceedings of the …, 2021‏ - openaccess.thecvf.com
Abstract Model-based 3D pose and shape estimation methods reconstruct a full 3D mesh for
the human body by estimating several parameters. However, learning the abstract …

Vibe: Video inference for human body pose and shape estimation

M Kocabas, N Athanasiou… - Proceedings of the IEEE …, 2020‏ - openaccess.thecvf.com
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 …