3D Human Pose Estimation

3D Human Pose Estimation is a computer vision task that involves estimating the 3D positions and orientations of body joints and bones from 2D images or videos. The goal is to reconstruct the 3D pose of a person in real-time, which can be used in a variety of applications, such as virtual reality, human-computer interaction, and motion analysis.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 321–330 of 665 papers

Title	Date	Tasks	Status	Score
3D Human Pose Estimation with 2D Marginal Heatmaps	Jun 5, 2018	3D Human Pose EstimationPose Estimation	CodeCode Available	5
HPERL: 3D Human Pose Estimation from RGB and LiDAR	Oct 16, 2020	3D Human Pose EstimationAction Recognition	CodeCode Available	5
How Robust is 3D Human Pose Estimation to Occlusion?	Aug 28, 2018	3D Human Pose Estimation3D Pose Estimation	CodeCode Available	5
Cooperative Inference for Real-Time 3D Human Pose Estimation in Multi-Device Edge Networks	Apr 3, 2025	3D Human Pose Estimation3D Pose Estimation	CodeCode Available	5
ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation	Dec 11, 2023	3D Human Pose EstimationMonocular 3D Human Pose Estimation	CodeCode Available	5
Convolutional Pose Machines	Jan 30, 2016	3D Human Pose EstimationCar Pose Estimation	CodeCode Available	5
Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation	Nov 17, 2016	3D Human Pose EstimationMonocular 3D Human Pose Estimation	CodeCode Available	5
Convolutional Mesh Regression for Single-Image Human Shape Reconstruction	May 8, 2019	3D geometry3D Hand Pose Estimation	CodeCode Available	5
Learning Temporal 3D Human Pose Estimation with Pseudo-Labels	Oct 14, 2021	3D Human Pose EstimationPose Estimation	CodeCode Available	5
Learning from Synthetic Humans	Jan 5, 2017	2D Human Pose Estimation3D Human Pose Estimation	CodeCode Available	5

Show:10 25 50

← PrevPage 33 of 67Next →

All datasets 3DPW MPI-INF-3DHP Human3.6M HumanEva-I H3WB Total Capture EMDB AGORA Panoptic Surreal 3D Poses in the Wild Challenge AIST++

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	Simple-baseline	PA-MPJPE	157	—	Unverified
2	HMR	MPJPE	130	—	Unverified
3	BMP	MPVPE	119.3	—	Unverified
4	SPIN	MPVPE	116.4	—	Unverified
5	Wenshuo et a;.	MPVPE	112.6	—	Unverified
6	TCMR (T=16 w/o 3DPW)	MPVPE	111.5	—	Unverified
7	CHOMP	MPVPE	110.1	—	Unverified
8	PC-HMR	MPVPE	108.6	—	Unverified
9	3DCrowdNet	MPVPE	108.5	—	Unverified
10	SMPLify	PA-MPJPE	106.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	VNect (Augm.)	MPJPE	124.7	—	Unverified
2	HMR	MPJPE	124.2	—	Unverified
3	Single-Shot Multi-Person	MPJPE	122.2	—	Unverified
4	Mehta	MPJPE	117.6	—	Unverified
5	PONet	MPJPE	115	—	Unverified
6	Pose Consensus (monocular)	MPJPE	112.1	—	Unverified
7	GeoRep (fully-supervised)	MPJPE	110.8	—	Unverified
8	XFormer (HRNet)	MPJPE	109.8	—	Unverified
9	EpipolarPose (fully-supervised)	MPJPE	108.99	—	Unverified
10	SPIN	MPJPE	105.2	—	Unverified