Papers › 3D Human Pose and Shape Estimation via HybrIK-Transformer

3D Human Pose and Shape Estimation via HybrIK-Transformer

9 Feb 2023arXiv:2302.04774archive 2025-07-28

Boris N. Oreshkin

HybrIK relies on a combination of analytical inverse kinematics and deep learning to produce more accurate 3D pose estimation from 2D monocular images. HybrIK has three major components: (1) pretrained convolution backbone, (2) deconvolution to lift 3D pose from 2D convolution features, (3) analytical inverse kinematics pass correcting deep learning prediction using learned distribution of plausible twist and swing angles. In this paper we propose an enhancement of the 2D to 3D lifting module, replacing deconvolution with Transformer, resulting in accuracy and computational efficiency improvement relative to the original HybrIK method. We demonstrate our results on commonly used H36M, PW3D, COCO and HP3D datasets. Our code is publicly available https://github.com/boreshkinai/hybrik-transformer.

Paper PDF Code

Code

boreshkinai/hybrik-transformer officialmentioned in papermentioned on GitHubpytorch 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 Pose Estimation 3D human pose and shape estimation Computational Efficiency Deep Learning Monocular 3D Human Pose Estimation Pose Estimation

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
3D Human Pose Estimation	3DPW	HybrIK-Transformer (HrNet-48)	MPJPE	71.6	#26 of 119	Archive leaderboard	report
3D Human Pose Estimation	3DPW	HybrIK-Transformer (HrNet-48)	MPVPE	83.6	#26 of 119	Archive leaderboard	report
3D Human Pose Estimation	3DPW	HybrIK-Transformer (HrNet-48)	PA-MPJPE	42.3	#26 of 119	Archive leaderboard	report
3D Human Pose Estimation	MPI-INF-3DHP	HybrIK-Transformer (HrNet-48)	AUC	48.9	#44 of 108	Archive leaderboard	report
3D Human Pose Estimation	MPI-INF-3DHP	HybrIK-Transformer (HrNet-48)	MPJPE	86.2	#44 of 108	Archive leaderboard	report
3D Human Pose Estimation	MPI-INF-3DHP	HybrIK-Transformer (HrNet-48)	PCK	88.6	#44 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 Convolution 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