SOTAVerified

3D Pose Estimation

Image credit: GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision , ECCV'20

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–150 of 379 papers

TitleStatusHype
Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes based on Monocular Camera and Single LiDAR—0
Kinematic-aware Hierarchical Attention Network for Human Pose Estimation in VideosCode1
Weakly-supervised Pre-training for 3D Human Pose Estimation via Perspective Knowledge—0
A Flexible-Frame-Rate Vision-Aided Inertial Object Tracking System for Mobile Devices—0
MEEV: Body Mesh Estimation On Egocentric VideoCode1
MC-hands-1M: A glove-wearing hand dataset for pose estimation—0
MotionBERT: A Unified Perspective on Learning Human Motion RepresentationsCode3
Decanus to Legatus: Synthetic training for 2D-3D human pose liftingCode0
K-Order Graph-oriented Transformer with GraAttention for 3D Pose and Shape Estimation—0
Visual Pursuit Control based on Gaussian Processes with Switched Motion TrajectoriesCode0
IVT: An End-to-End Instance-guided Video Transformer for 3D Pose Estimation—0
Translating a Visual LEGO Manual to a Machine-Executable Plan—0
Dynamic Graph Reasoning for Multi-person 3D Pose Estimation—0
Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic ProjectionCode1
VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual DataCode1
Multi-person 3D pose estimation from a single image captured by a fisheye camera—0
Snipper: A Spatiotemporal Transformer for Simultaneous Multi-Person 3D Pose Estimation Tracking and Forecasting on a Video SnippetCode1
PoseGU: 3D Human Pose Estimation with Novel Human Pose Generator and Unbiased Learning—0
Ego2HandsPose: A Dataset for Egocentric Two-hand 3D Global Pose Estimation—0
Building Spatio-temporal Transformers for Egocentric 3D Pose Estimation—0
VTP: Volumetric Transformer for Multi-view Multi-person 3D Pose Estimation—0
"Teaching Independent Parts Separately" (TIPSy-GAN) : Improving Accuracy and Stability in Unsupervised Adversarial 2D to 3D Pose Estimation—0
Dual networks based 3D Multi-Person Pose Estimation from Monocular VideoCode1
Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolution—0
Integrated In-vehicle Monitoring System Using 3D Human Pose Estimation and Seat Belt Segmentation—0
3D Human Pose Estimation for Free-from and Moving Activities Using WiFi—0
What's in your hands? 3D Reconstruction of Generic Objects in HandsCode1
Permutation-Invariant Relational Network for Multi-person 3D Pose Estimation—0
On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation—0
RayTran: 3D pose estimation and shape reconstruction of multiple objects from videos with ray-traced transformers—0
DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose EstimationCode1
Distribution-Aware Single-Stage Models for Multi-Person 3D Pose EstimationCode1
ConDor: Self-Supervised Canonicalization of 3D Pose for Partial ShapesCode1
Graph Neural Networks for Cross-Camera Data AssociationCode1
Mushrooms Detection, Localization and 3D Pose Estimation using RGB-D Sensor for Robotic-picking Applications—0
Enhancing Egocentric 3D Pose Estimation with Third Person ViewsCode0
GraFormer: Graph-Oriented Transformer for 3D Pose Estimation—0
Single-Stage Is Enough: Multi-Person Absolute 3D Pose Estimation—0
Rethinking the Data Annotation Process for Multi-view 3D Pose Estimation with Active Learning and Self-TrainingCode1
SmoothNet: A Plug-and-Play Network for Refining Human Poses in VideosCode1
Local and Global Point Cloud Reconstruction for 3D Hand Pose EstimationCode1
OOD-CV: A Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images—0
3D Pose Estimation and Future Motion Prediction from 2D Images—0
Lifting 2D Human Pose to 3D with Domain Adapted 3D Body Concept—0
Direct Multi-view Multi-person 3D Pose EstimationCode1
Higher-Order Implicit Fairing Networks for 3D Human Pose Estimation—0
Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D PoseCode1
TransFusion: Cross-view Fusion with Transformer for 3D Human Pose EstimationCode1
HUMAN4D: A Human-Centric Multimodal Dataset for Motions and Immersive MediaCode1
Real-time, low-cost multi-person 3D pose estimation—0
Show:102550
← PrevPage 3 of 8Next →
All datasetsHuman3.6MGoogle-ARGoogle-YogaCarFusionHARPERK2HPD

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Liftformer (n=27 CPN)Average MPJPE (mm)48.6—Unverified
2Liftformer (n=81 CPN)Average MPJPE (mm)46—Unverified
3Liftformer (n=243 CPN)Average MPJPE (mm)44.8—Unverified
4TesseTrackAverage MPJPE (mm)18.7—Unverified
#ModelMetricClaimedVerifiedStatus
1OpenPose (body only)PCK@0.287.8—Unverified
2BlazePose FullPCK@0.284.1—Unverified
3BlazePose LitePCK@0.279.6—Unverified
#ModelMetricClaimedVerifiedStatus
1BlazePose FullPCK@0.284.5—Unverified
2OpenPose (body only)PCK@0.283.4—Unverified
3BlazePose LitePCK@0.277.6—Unverified
#ModelMetricClaimedVerifiedStatus
1Occlusion-NET3DPCK93.2—Unverified
#ModelMetricClaimedVerifiedStatus
1HRNet + DepthAverage MPJPE (mm)151—Unverified
#ModelMetricClaimedVerifiedStatus
1A2JFPS93.78—Unverified