SOTAVerified

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

Showing 201–250 of 4228 papers

TitleStatusHype
CAD-Estate: Large-scale CAD Model Annotation in RGB VideosCode1
Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-LearningCode1
Direct Multi-view Multi-person 3D Pose EstimationCode1
AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the WildCode1
BundleFusion: Real-time Globally Consistent 3D Reconstruction using On-the-fly Surface Re-integrationCode1
DiffusionNOCS: Managing Symmetry and Uncertainty in Sim2Real Multi-Modal Category-level Pose EstimationCode1
DirectPose: Direct End-to-End Multi-Person Pose EstimationCode1
DistilPose: Tokenized Pose Regression with Heatmap DistillationCode1
Bottom-Up Human Pose Estimation by Ranking Heatmap-Guided Adaptive Keypoint EstimatesCode1
DiffPose: Toward More Reliable 3D Pose EstimationCode1
Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis AggregationCode1
BOP: Benchmark for 6D Object Pose EstimationCode1
Bootstrapping Human Optical Flow and PoseCode1
BRACE: The Breakdancing Competition Dataset for Dance Motion SynthesisCode1
Diffusion-based Pose Refinement and Muti-hypothesis Generation for 3D Human Pose EstimaitonCode1
BodySLAM: A Generalized Monocular Visual SLAM Framework for Surgical ApplicationsCode1
Activating Self-Attention for Multi-Scene Absolute Pose RegressionCode1
Boosting 3-DoF Ground-to-Satellite Camera Localization Accuracy via Geometry-Guided Cross-View TransformerCode1
Learning Loss for Active LearningCode1
Bimodal Camera Pose Prediction for EndoscopyCode1
3D Neural Embedding Likelihood: Probabilistic Inverse Graphics for Robust 6D Pose EstimationCode1
Cascaded Pyramid Network for Multi-Person Pose EstimationCode1
Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic ParsingCode1
Diffusion-Driven Self-Supervised Learning for Shape Reconstruction and Pose EstimationCode1
Distribution-Aware Single-Stage Models for Multi-Person 3D Pose EstimationCode1
BLAPose: Enhancing 3D Human Pose Estimation with Bone Length AdjustmentCode1
3D-MuPPET: 3D Multi-Pigeon Pose Estimation and TrackingCode1
Body2Hands: Learning to Infer 3D Hands from Conversational Gesture Body DynamicsCode1
Benchmarking Image Retrieval for Visual LocalizationCode1
BoIR: Box-Supervised Instance Representation for Multi-Person Pose EstimationCode1
Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded ScenesCode1
Active Learning for Bayesian 3D Hand Pose EstimationCode1
BEV-Net: Assessing Social Distancing Compliance by Joint People Localization and Geometric ReasoningCode1
Rethinking the Data Annotation Process for Multi-view 3D Pose Estimation with Active Learning and Self-TrainingCode1
Bottom-Up Human Pose Estimation Via Disentangled Keypoint RegressionCode1
Bottom-Up and Top-Down Reasoning with Hierarchical Rectified GaussiansCode1
3DP3: 3D Scene Perception via Probabilistic ProgrammingCode1
Active Transfer Learning for Efficient Video-Specific Human Pose EstimationCode1
Towards Accurate Active Camera LocalizationCode1
Breaking the Frame: Visual Place Recognition by Overlap PredictionCode1
DETRs with Hybrid MatchingCode1
BST: Badminton Stroke-type Transformer for Skeleton-based Action Recognition in Racket SportsCode1
CAD2Render: A Modular Toolkit for GPU-accelerated Photorealistic Synthetic Data Generation for the Manufacturing IndustryCode1
BVMatch: Lidar-based Place Recognition Using Bird's-eye View ImagesCode1
Bayesian Inverse Graphics for Few-Shot Concept LearningCode1
DiffusionRegPose: Enhancing Multi-Person Pose Estimation using a Diffusion-Based End-to-End Regression ApproachCode1
BaseBoostDepth: Exploiting Larger Baselines For Self-supervised Monocular Depth EstimationCode1
CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the WildCode1
Capturing the motion of every joint: 3D human pose and shape estimation with independent tokensCode1
Beyond Cross-view Image Retrieval: Highly Accurate Vehicle Localization Using Satellite ImageCode1
Show:102550
← PrevPage 5 of 85Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1yoloposeAP5090.3—Unverified
2ViTPose (ViTAE-G, ensemble)AP81.1—Unverified
3ViTPose (ViTAE-G)AP80.9—Unverified
4PoseBH-HAP79.5—Unverified
5UDP-Pose-PSA(384x288)AP79.5—Unverified
64xRSN-50 (ensemble)AP79.2—Unverified
7UDP-Pose-PSA(256x192)AP78.9—Unverified
8CCM+AP78.9—Unverified
94xRSN-50AP78.6—Unverified
10PCT (256x256)AP78.3—Unverified
#ModelMetricClaimedVerifiedStatus
1PCT (swin-l, test set)PCKh-0.594.3—Unverified
2Soft-gated Skip ConnectionsPCKh-0.594.1—Unverified
3Cascade Feature AggregationPCKh-0.593.9—Unverified
4PCT (swin-b, test set)PCKh-0.593.8—Unverified
5TransPosePCKh-0.593.5—Unverified
6UniHCP (FT)PCKh-0.593.2—Unverified
74xRSN-50PCKh-0.593—Unverified
8UniPosePCKh-0.592.7—Unverified
9MSPNPCKh-0.592.6—Unverified
10Spatial ContextPCKh-0.592.5—Unverified
#ModelMetricClaimedVerifiedStatus
1ViTPose (ViTAE-G, GT bounding boxes)Test AP93.3—Unverified
2UniHCP (direct eval)Test AP87.4—Unverified
3PoseBH-HTest AP87—Unverified
4RTMPose(RTMPose-l, GT bounding boxes)Test AP80.3—Unverified
5TransPose-HValidation AP62.3—Unverified
6BBox-Mask-Pose 2xTest AP48.3—Unverified
7BUCTD (CID-W32)Test AP47.2—Unverified
8HQNet (ViT-L)Test AP45.6—Unverified
9MaskPose-bTest AP45—Unverified
10CID (HRNet-W48)Test AP45—Unverified
#ModelMetricClaimedVerifiedStatus
1OmniPosePCK99.5—Unverified
2Soft-gated Skip ConnectionsPCK94.8—Unverified
3Residual Hourglass + ASR + AHOPCK94.5—Unverified
4UniPosePCK94.5—Unverified
5Chou et al. arXiv'17PCK94—Unverified
6Pyramid Residual Modules (PRMs)PCK93.9—Unverified
7Stacked hourglass + Inception-resnetPCK93.9—Unverified
8Multi-Context AttentionPCK92.6—Unverified
9FPDPCK90.8—Unverified
10Part heatmap regression (ResNet-152)PCK90.7—Unverified
#ModelMetricClaimedVerifiedStatus
1BUCTD-W48 (w/cond. input from PETR, and generative sampling)AP78.5—Unverified
2ViTPose-GAP78.3—Unverified
3BUCTD-W48 (w/cond. input from PETR)AP76.7—Unverified
4SwinV2-L 1K-MIMAP75.5—Unverified
5SwinV2-B 1K-MIMAP74.9—Unverified
6BUCTD-W48AP72.9—Unverified
7OpenPifPafAP70.5—Unverified
8MIPNet (HRNet-W48)AP70—Unverified
9KAPAO-LAP68.9—Unverified
10KAPAO-MAP67.1—Unverified
#ModelMetricClaimedVerifiedStatus
1CCNet (ViTPose-B_GT-bbox_256x192)AP78.1—Unverified
2MogaNet-B (384x288)AP77.3—Unverified
3ViTPose-B (Single-task_GT-bbox_256x192)AP77.3—Unverified
4MogaNet-S (384x288)AP76.4—Unverified
5Bias (HRNet_256x192)AP75.8—Unverified
6ViTPose-B (Single-task_Det-bbox_256x192)AP75.8—Unverified
7HRNet (256x192)AP75.3—Unverified
8MogaNet-S (256x192)AP74.9—Unverified
9MogaNet-T (256x192)AP73.2—Unverified
10RLE (256x192)AP71.3—Unverified
#ModelMetricClaimedVerifiedStatus
1Hulk(Finetune, ViT-L)AP37.1—Unverified
2Hulk(Finetune, ViT-B)AP35.6—Unverified
3HRFormer (HRFomer-B)AP34.4—Unverified
4UniHCP (finetune)AP33.6—Unverified
5HRNet (HRNet-w48 )AP33.5—Unverified
6HRNet (HRNet-w32)AP32.3—Unverified
7HRFormer (HRFomer-S)AP31.6—Unverified
8SimpleBaseline (ResNet-152)AP29.9—Unverified
9SimpleBaseline (ResNet-101)AP29.4—Unverified
10SimpleBaseline (ResNet-50)AP28—Unverified
#ModelMetricClaimedVerifiedStatus
1BUCTD (PETR, with generative sampling)APL83.7—Unverified
2OmniPose (WASPv2)AP79.5—Unverified
3MetaPrompt-SDAP79—Unverified
4Hulk(Finetune, ViT-L)AP78.7—Unverified
5BUCTD (PETR, with generative sampling)AP77.8—Unverified
6Hulk(Finetune, ViT-B)AP77.5—Unverified
7I²R-Net (1st stage:HRFormer-B)AP77.3—Unverified
8PATH (Partial FT)AP77.1—Unverified
9SOLIDER (swin-B)AP76.6—Unverified
10PEFORMER-Xcit-dino-p8AP72.6—Unverified
#ModelMetricClaimedVerifiedStatus
1GIM-DKM[email protected],10°57.1—Unverified
2GIM-LoFTR[email protected],10°54.5—Unverified
3GIM-SuperGlue[email protected],10°53.5—Unverified
4DKM[email protected],10°51.5—Unverified
5SuperGlue[email protected],10°49—Unverified
6LoFTR[email protected],10°47.5—Unverified
#ModelMetricClaimedVerifiedStatus
1AdaPoseMean mAP93.38—Unverified
2DECA-D3Mean mAP88.75—Unverified
3V2V-PoseNetMean mAP88.74—Unverified
4A2JMean mAP88—Unverified
5RENMean mAP84.9—Unverified
6Multi-task learning + viewpoint invarianceMean mAP77.4—Unverified
#ModelMetricClaimedVerifiedStatus
1SimpleBaseline + HANetMean [email protected]99.6—Unverified
2DeciWatchMean [email protected]99—Unverified
3LSTM PMMean [email protected]93.6—Unverified
4CPMMean [email protected]91.9—Unverified
5UniTrack_i18Mean [email protected]80.5—Unverified
#ModelMetricClaimedVerifiedStatus
14xRSN-50[email protected]93—Unverified
2Refine[email protected]92.1—Unverified
3EfficientPose IV[email protected]91.2—Unverified
4OpenPose[email protected]88.8—Unverified
5Adversarial Learning[email protected]88.6—Unverified
#ModelMetricClaimedVerifiedStatus
1OmniPoseMean [email protected]99.4—Unverified
2UniPose-LSTMMean [email protected]99.3—Unverified
3LSTM PMMean [email protected]97.7—Unverified
4Thin-SlicingMean [email protected]96.5—Unverified
5Iqbal et al.Mean [email protected]81.1—Unverified
#ModelMetricClaimedVerifiedStatus
1DP-RCNN-DeepLab (ResNet-101)AP68—Unverified