Pose Estimation

Pose Estimation is a computer vision task where the goal is to detect the position and orientation of a person or an object. Usually, this is done by predicting the location of specific keypoints like hands, head, elbows, etc. in case of Human Pose Estimation.

A common benchmark for this task is MPII Human Pose

( Image credit: Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose )

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 101–150 of 4228 papers

Title	Date	Tasks	Status	Hype	Score
HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining	Mar 10, 2023	AttributeAutonomous Driving	CodeCode Available	2	5
Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes	Mar 5, 2023	3D Human Pose EstimationHuman Detection	CodeCode Available	2	5
HumanMM: Global Human Motion Recovery from Multi-shot Videos	Mar 10, 2025	Camera Pose EstimationMotion Generation	CodeCode Available	2	5
IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos	Nov 18, 2024	Pose EstimationSemantic Segmentation	CodeCode Available	2	5
Keypoint-Based Category-Level Object Pose Tracking from an RGB Sequence with Uncertainty Estimation	May 23, 2022	Pose EstimationPose Tracking	CodeCode Available	2	5
Hierarchical NeuroSymbolic Approach for Comprehensive and Explainable Action Quality Assessment	Mar 20, 2024	Action Quality AssessmentAction Quality Assessment Report Generation	CodeCode Available	2	5
H3WB: Human3.6M 3D WholeBody Dataset and Benchmark	Nov 28, 2022	3D Facial Landmark Localization3D Hand Pose Estimation	CodeCode Available	2	5
HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields	Feb 26, 2024	3D Hand Pose Estimationhand-object pose	CodeCode Available	2	5
NOPE: Novel Object Pose Estimation from a Single Image	Mar 23, 2023	ObjectPose Estimation	CodeCode Available	2	5
GST: Precise 3D Human Body from a Single Image with Gaussian Splatting Transformers	Sep 6, 2024	3DGS3D human pose and shape estimation	CodeCode Available	2	5
GV-Bench: Benchmarking Local Feature Matching for Geometric Verification of Long-term Loop Closure Detection	Jul 16, 2024	BenchmarkingLoop Closure Detection	CodeCode Available	2	5
OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association	Mar 3, 2021	Car Pose EstimationKeypoint Detection	CodeCode Available	2	5
An Open-Source American Sign Language Fingerspell Recognition and Semantic Pose Retrieval Interface	Aug 17, 2024	Pose EstimationPose Retrieval	CodeCode Available	2	5
Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation	Nov 20, 2023	3D Human Pose EstimationPose Estimation	CodeCode Available	2	5
POMATO: Marrying Pointmap Matching with Temporal Motion for Dynamic 3D Reconstruction	Apr 8, 2025	3D ReconstructionDepth Estimation	CodeCode Available	2	5
A Graph-Based Approach for Category-Agnostic Pose Estimation	Nov 29, 2023	2D Pose EstimationAnimal Pose Estimation	CodeCode Available	2	5
Pose for Everything: Towards Category-Agnostic Pose Estimation	Jul 21, 2022	2D Pose EstimationCategory-Agnostic Pose Estimation	CodeCode Available	2	5
PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation	Mar 30, 2023	3D Human Pose EstimationClassification	CodeCode Available	2	5
A Simple Baseline for Efficient Hand Mesh Reconstruction	Mar 4, 2024	3D Hand Pose EstimationComputational Efficiency	CodeCode Available	2	5
COALA: A Practical and Vision-Centric Federated Learning Platform	Jul 23, 2024	BenchmarkingContinual Learning	CodeCode Available	2	5
GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splatting	Jan 23, 2025	3DGSNeRF	CodeCode Available	2	5
CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation	Mar 3, 2022	3D Reconstruction3D Shape Reconstruction	CodeCode Available	2	5
Recollection from Pensieve: Novel View Synthesis via Learning from Uncalibrated Videos	May 19, 2025	3D geometryCamera Pose Estimation	CodeCode Available	2	5
Reconstructing 3D Human Pose by Watching Humans in the Mirror	Apr 1, 2021	3D Pose EstimationPose Estimation	CodeCode Available	2	5
GRPose: Learning Graph Relations for Human Image Generation with Pose Priors	Aug 29, 2024	Image GenerationPose Estimation	CodeCode Available	2	5
GSLoc: Efficient Camera Pose Refinement via 3D Gaussian Splatting	Aug 20, 2024	3DGSNeRF	CodeCode Available	2	5
GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction	Sep 5, 2023	3D Reconstructionglobal-optimization	CodeCode Available	2	5
BlenderProc	Oct 25, 2019	3D Object RecognitionDepth Image Estimation	CodeCode Available	2	5
Graduated Non-Convexity for Robust Spatial Perception: From Non-Minimal Solvers to Global Outlier Rejection	Sep 18, 2019	Pose Estimation	CodeCode Available	2	5
GSplatLoc: Ultra-Precise Camera Localization via 3D Gaussian Splatting	Dec 28, 2024	Camera LocalizationPose Estimation	CodeCode Available	2	5
Hulk: A Universal Knowledge Translator for Human-Centric Tasks	Dec 4, 2023	3D Human Pose EstimationAction Recognition	CodeCode Available	2	5
KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation	Mar 31, 2024	3D Human Pose EstimationMonocular 3D Human Pose Estimation	CodeCode Available	2	5
Advancing 6-DoF Instrument Pose Estimation in Variable X-Ray Imaging Geometries	May 19, 2024	6D Pose EstimationGPU	CodeCode Available	2	5
GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence	Nov 23, 2023	3D Reconstruction6D Pose Estimation	CodeCode Available	2	5
Balanced MSE for Imbalanced Visual Regression	Mar 30, 2022	Age EstimationFairness	CodeCode Available	2	5
Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images	Apr 22, 2022	ObjectPose Estimation	CodeCode Available	2	5
GLACE: Global Local Accelerated Coordinate Encoding	Jun 6, 2024	Camera Pose EstimationPose Estimation	CodeCode Available	2	5
FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Models	May 8, 2024	3D Human Pose EstimationDenoising	CodeCode Available	2	5
Fast and Flexible Human Pose Estimation with HyperPose	Aug 26, 2021	Pose Estimation	CodeCode Available	2	5
FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration	Aug 13, 2021	3D Human Pose Estimation3D Human Reconstruction	CodeCode Available	2	5
MogaNet: Multi-order Gated Aggregation Network	Nov 7, 2022	3D Human Pose EstimationImage Classification	CodeCode Available	2	5
Face Alignment in Full Pose Range: A 3D Total Solution	Apr 2, 2018	3D Pose EstimationDepth Image Estimation	CodeCode Available	2	5
Free-SurGS: SfM-Free 3D Gaussian Splatting for Surgical Scene Reconstruction	Jul 3, 2024	3DGS3D Reconstruction	CodeCode Available	2	5
Global Context for Convolutional Pose Machines	Jun 10, 2019	Pose EstimationSemantic Segmentation	CodeCode Available	2	5
AutoSoccerPose: Automated 3D posture Analysis of Soccer Shot Movements	May 20, 2024	3D Pose EstimationPose Estimation	CodeCode Available	2	5
DETRPose: Real-time end-to-end transformer model for multi-person pose estimation	Jun 16, 2025	2D Pose EstimationDecoder	CodeCode Available	2	5
3D Human Mesh Estimation from Virtual Markers	Mar 21, 2023	3D Human Pose Estimation3D Pose Estimation	CodeCode Available	2	5
AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing	Jul 27, 2022	Mixed RealityPose Estimation	CodeCode Available	2	5
Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose Estimation	Feb 4, 2025	DenoisingDomain Generalization	CodeCode Available	2	5
Does Image Anonymization Impact Computer Vision Training?	Jun 8, 2023	Face AnonymizationInstance Segmentation	CodeCode Available	2	5

Show:10 25 50

← PrevPage 3 of 85Next →

All datasets COCO test-dev MPII Human Pose OCHuman Leeds Sports Poses CrowdPose COCO val2017 AIC COCO (Common Objects in Context)InLoc ITOP front-view J-HMDB MPII Single Person

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	yolopose	AP50	90.3	—	Unverified
2	ViTPose (ViTAE-G, ensemble)	AP	81.1	—	Unverified
3	ViTPose (ViTAE-G)	AP	80.9	—	Unverified
4	PoseBH-H	AP	79.5	—	Unverified
5	UDP-Pose-PSA(384x288)	AP	79.5	—	Unverified
6	4xRSN-50 (ensemble)	AP	79.2	—	Unverified
7	UDP-Pose-PSA(256x192)	AP	78.9	—	Unverified
8	CCM+	AP	78.9	—	Unverified
9	4xRSN-50	AP	78.6	—	Unverified
10	PCT (256x256)	AP	78.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	PCT (swin-l, test set)	PCKh-0.5	94.3	—	Unverified
2	Soft-gated Skip Connections	PCKh-0.5	94.1	—	Unverified
3	Cascade Feature Aggregation	PCKh-0.5	93.9	—	Unverified
4	PCT (swin-b, test set)	PCKh-0.5	93.8	—	Unverified
5	TransPose	PCKh-0.5	93.5	—	Unverified
6	UniHCP (FT)	PCKh-0.5	93.2	—	Unverified
7	4xRSN-50	PCKh-0.5	93	—	Unverified
8	UniPose	PCKh-0.5	92.7	—	Unverified
9	MSPN	PCKh-0.5	92.6	—	Unverified
10	Spatial Context	PCKh-0.5	92.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ViTPose (ViTAE-G, GT bounding boxes)	Test AP	93.3	—	Unverified
2	UniHCP (direct eval)	Test AP	87.4	—	Unverified
3	PoseBH-H	Test AP	87	—	Unverified
4	RTMPose(RTMPose-l, GT bounding boxes)	Test AP	80.3	—	Unverified
5	TransPose-H	Validation AP	62.3	—	Unverified
6	BBox-Mask-Pose 2x	Test AP	48.3	—	Unverified
7	BUCTD (CID-W32)	Test AP	47.2	—	Unverified
8	HQNet (ViT-L)	Test AP	45.6	—	Unverified
9	MaskPose-b	Test AP	45	—	Unverified
10	CID (HRNet-W48)	Test AP	45	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	OmniPose	PCK	99.5	—	Unverified
2	Soft-gated Skip Connections	PCK	94.8	—	Unverified
3	Residual Hourglass + ASR + AHO	PCK	94.5	—	Unverified
4	UniPose	PCK	94.5	—	Unverified
5	Chou et al. arXiv'17	PCK	94	—	Unverified
6	Pyramid Residual Modules (PRMs)	PCK	93.9	—	Unverified
7	Stacked hourglass + Inception-resnet	PCK	93.9	—	Unverified
8	Multi-Context Attention	PCK	92.6	—	Unverified
9	FPD	PCK	90.8	—	Unverified
10	Part heatmap regression (ResNet-152)	PCK	90.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BUCTD-W48 (w/cond. input from PETR, and generative sampling)	AP	78.5	—	Unverified
2	ViTPose-G	AP	78.3	—	Unverified
3	BUCTD-W48 (w/cond. input from PETR)	AP	76.7	—	Unverified
4	SwinV2-L 1K-MIM	AP	75.5	—	Unverified
5	SwinV2-B 1K-MIM	AP	74.9	—	Unverified
6	BUCTD-W48	AP	72.9	—	Unverified
7	OpenPifPaf	AP	70.5	—	Unverified
8	MIPNet (HRNet-W48)	AP	70	—	Unverified
9	KAPAO-L	AP	68.9	—	Unverified
10	KAPAO-M	AP	67.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CCNet (ViTPose-B_GT-bbox_256x192)	AP	78.1	—	Unverified
2	MogaNet-B (384x288)	AP	77.3	—	Unverified
3	ViTPose-B (Single-task_GT-bbox_256x192)	AP	77.3	—	Unverified
4	MogaNet-S (384x288)	AP	76.4	—	Unverified
5	Bias (HRNet_256x192)	AP	75.8	—	Unverified
6	ViTPose-B (Single-task_Det-bbox_256x192)	AP	75.8	—	Unverified
7	HRNet (256x192)	AP	75.3	—	Unverified
8	MogaNet-S (256x192)	AP	74.9	—	Unverified
9	MogaNet-T (256x192)	AP	73.2	—	Unverified
10	RLE (256x192)	AP	71.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Hulk(Finetune, ViT-L)	AP	37.1	—	Unverified
2	Hulk(Finetune, ViT-B)	AP	35.6	—	Unverified
3	HRFormer (HRFomer-B)	AP	34.4	—	Unverified
4	UniHCP (finetune)	AP	33.6	—	Unverified
5	HRNet (HRNet-w48 )	AP	33.5	—	Unverified
6	HRNet (HRNet-w32)	AP	32.3	—	Unverified
7	HRFormer (HRFomer-S)	AP	31.6	—	Unverified
8	SimpleBaseline (ResNet-152)	AP	29.9	—	Unverified
9	SimpleBaseline (ResNet-101)	AP	29.4	—	Unverified
10	SimpleBaseline (ResNet-50)	AP	28	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BUCTD (PETR, with generative sampling)	APL	83.7	—	Unverified
2	OmniPose (WASPv2)	AP	79.5	—	Unverified
3	MetaPrompt-SD	AP	79	—	Unverified
4	Hulk(Finetune, ViT-L)	AP	78.7	—	Unverified
5	BUCTD (PETR, with generative sampling)	AP	77.8	—	Unverified
6	Hulk(Finetune, ViT-B)	AP	77.5	—	Unverified
7	I²R-Net (1st stage:HRFormer-B)	AP	77.3	—	Unverified
8	PATH (Partial FT)	AP	77.1	—	Unverified
9	SOLIDER (swin-B)	AP	76.6	—	Unverified
10	PEFORMER-Xcit-dino-p8	AP	72.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	GIM-DKM	DUC1-Acc@0.25m,10°	57.1	—	Unverified
2	GIM-LoFTR	DUC1-Acc@0.25m,10°	54.5	—	Unverified
3	GIM-SuperGlue	DUC1-Acc@0.25m,10°	53.5	—	Unverified
4	DKM	DUC1-Acc@0.25m,10°	51.5	—	Unverified
5	SuperGlue	DUC1-Acc@0.25m,10°	49	—	Unverified
6	LoFTR	DUC1-Acc@0.25m,10°	47.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	AdaPose	Mean mAP	93.38	—	Unverified
2	DECA-D3	Mean mAP	88.75	—	Unverified
3	V2V-PoseNet	Mean mAP	88.74	—	Unverified
4	A2J	Mean mAP	88	—	Unverified
5	REN	Mean mAP	84.9	—	Unverified
6	Multi-task learning + viewpoint invariance	Mean mAP	77.4	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SimpleBaseline + HANet	Mean PCK@0.2	99.6	—	Unverified
2	DeciWatch	Mean PCK@0.2	99	—	Unverified
3	LSTM PM	Mean PCK@0.2	93.6	—	Unverified
4	CPM	Mean PCK@0.2	91.9	—	Unverified
5	UniTrack_i18	Mean PCK@0.2	80.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	4xRSN-50	PCKh@0.5	93	—	Unverified
2	Refine	PCKh@0.5	92.1	—	Unverified
3	EfficientPose IV	PCKh@0.5	91.2	—	Unverified
4	OpenPose	PCKh@0.5	88.8	—	Unverified
5	Adversarial Learning	PCKh@0.5	88.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	OmniPose	Mean PCK@0.2	99.4	—	Unverified
2	UniPose-LSTM	Mean PCK@0.2	99.3	—	Unverified
3	LSTM PM	Mean PCK@0.2	97.7	—	Unverified
4	Thin-Slicing	Mean PCK@0.2	96.5	—	Unverified
5	Iqbal et al.	Mean PCK@0.2	81.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DP-RCNN-DeepLab (ResNet-101)	AP	68	—	Unverified