Papers › Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation

Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation

26 Mar 2023CVPR 2023 1arXiv:2303.14747archive 2025-07-28

Xiaolong Shen, Zongxin Yang, Xiaohan Wang, Jianxin Ma, Chang Zhou, Yi Yang

Video-based 3D human pose and shape estimations are evaluated by intra-frame accuracy and inter-frame smoothness. Although these two metrics are responsible for different ranges of temporal consistency, existing state-of-the-art methods treat them as a unified problem and use monotonous modeling structures (e.g., RNN or attention-based block) to design their networks. However, using a single kind of modeling structure is difficult to balance the learning of short-term and long-term temporal correlations, and may bias the network to one of them, leading to undesirable predictions like global location shift, temporal inconsistency, and insufficient local details. To solve these problems, we propose to structurally decouple the modeling of long-term and short-term correlations in an end-to-end framework, Global-to-Local Transformer (GLoT). First, a global transformer is introduced with a Masked Pose and Shape Estimation strategy for long-term modeling. The strategy stimulates the global transformer to learn more inter-frame correlations by randomly masking the features of several frames. Second, a local transformer is responsible for exploiting local details on the human mesh and interacting with the global transformer by leveraging cross-attention. Moreover, a Hierarchical Spatial Correlation Regressor is further introduced to refine intra-frame estimations by decoupled global-local representation and implicit kinematic constraints. Our GLoT surpasses previous state-of-the-art methods with the lowest model parameters on popular benchmarks, i.e., 3DPW, MPI-INF-3DHP, and Human3.6M. Codes are available at https://github.com/sxl142/GLoT.

Paper PDF Conference PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

sxl142/glot officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Human Pose Estimation 3D human pose and shape estimation

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
3D Human Pose Estimation	3DPW	GLoT	Acceleration Error	6.6	#42 of 119	Archive leaderboard	report
3D Human Pose Estimation	3DPW	GLoT	MPJPE	80.7	#42 of 119	Archive leaderboard	report
3D Human Pose Estimation	3DPW	GLoT	MPVPE	96.3	#42 of 119	Archive leaderboard	report
3D Human Pose Estimation	3DPW	GLoT	PA-MPJPE	50.6	#42 of 119	Archive leaderboard	report
3D Human Pose Estimation	MPI-INF-3DHP	GLoT	Acceleration Error	7.9	#52 of 108	Archive leaderboard	report
3D Human Pose Estimation	MPI-INF-3DHP	GLoT	MPJPE	93.9	#52 of 108	Archive leaderboard	report
3D Human Pose Estimation	MPI-INF-3DHP	GLoT	PA-MPJPE	61.5	#52 of 108	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position Encodings Adam Attention BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections