|
CanonPose
|
CanonPose: Self-Supervised Monocular 3D Human Pos…
|
74.30
|
2020-11-30
|
|
|
VIBE
|
VIBE: Video Inference for Human Body Pose and Sha…
|
65.60
|
2019-12-11
|
|
|
VoxelKeypointFusion (transfer)
|
VoxelKeypointFusion: Generalizable Multi-View Mul…
|
64.30
|
2024-10-24
|
|
|
SIM (SH detections FT) (MA)
|
A simple yet effective baseline for 3d human pose…
|
62.90
|
2017-05-08
|
|
|
2D-3D Lifting self-supervised
|
Self-Supervised 3D Human Pose Estimation with Mul…
|
62.00
|
2021-08-17
|
|
|
Probabilistic Monocular (T=1)
|
Probabilistic Monocular 3D Human Pose Estimation …
|
61.80
|
2021-07-29
|
|
|
TAPE (T=16)
|
TAPE: Temporal Attention-based Probabilistic huma…
|
60.00
|
2023-04-29
|
|
|
Sequence-to-sequence network
|
Exploiting temporal information for 3D pose estim…
|
58.50
|
2017-11-23
|
|
|
Stereoscopic View Synthesis Subnetwork
|
Generalizing Monocular 3D Human Pose Estimation i…
|
58.00
|
2019-04-11
|
|
|
SemGCN
|
Semantic Graph Convolutional Networks for 3D Huma…
|
57.60
|
2019-04-06
|
|
|
MDN
|
Generating Multiple Hypotheses for 3D Human Pose …
|
52.70
|
2019-04-11
|
|
|
PoseLifter
|
PoseLifter: Absolute 3D human pose lifting networ…
|
52.50
|
2019-10-26
|
|
|
MöbiusGCN
|
3D Human Pose Estimation Using Möbius Graph Convo…
|
52.10
|
2022-03-20
|
|
|
Pose Consensus (monocular)
|
Consensus-based Optimization for 3D Human Pose Es…
|
52.00
|
2019-11-21
|
|
|
Graph Stacked Hourglass Network (CPN)
|
Graph Stacked Hourglass Networks for 3D Human Pos…
|
51.90
|
2021-03-30
|
|
|
VideoPose3D (T=1)
|
3D human pose estimation in video with temporal c…
|
51.80
|
2018-11-28
|
|
|
LoCO
|
Compressed Volumetric Heatmaps for Multi-Person 3…
|
51.10
|
2020-04-01
|
|
|
TAG-Net
|
Cascaded deep monocular 3D human pose estimation …
|
50.90
|
2020-06-14
|
|
|
HR-Net+ST-GCN+PoseAug
|
PoseAug: A Differentiable Pose Augmentation Frame…
|
50.80
|
2021-05-06
|
|
|
MTF-Transformer (M=0.4, T=1, N=1)
|
Adaptive Multi-view and Temporal Fusing Transform…
|
50.70
|
2021-10-11
|
|
|
Multi-view Temporal self-supervised
|
Learning Temporal 3D Human Pose Estimation with P…
|
50.60
|
2021-10-14
|
|
|
Jointformer (CPN)
|
Jointformer: Single-Frame Lifting Transformer wit…
|
50.50
|
2022-08-07
|
|
|
HR-Net+VPose+PoseAug
|
PoseAug: A Differentiable Pose Augmentation Frame…
|
50.20
|
2021-05-06
|
|
|
SRNet (T=1)
|
SRNet: Improving Generalization in 3D Human Pose …
|
49.90
|
2020-07-18
|
|
|
Ray3D (T=9 CPN)
|
Ray3D: ray-based 3D human pose estimation for mon…
|
49.70
|
2022-03-22
|
|
|
MDN (Multi-View)
|
Generating Multiple Hypotheses for 3D Human Pose …
|
49.60
|
2019-04-11
|
|
|
PGFormer (CPN)
|
Learning Pyramid-structured Long-range Dependenci…
|
49.50
|
2025-06-03
|
|
|
MTF-Transformer (M=0.4, T=7, N=1)
|
Adaptive Multi-view and Temporal Fusing Transform…
|
49.40
|
2021-10-11
|
|
|
Dual network
|
Dual networks based 3D Multi-Person Pose Estimati…
|
49.31
|
2022-05-02
|
|
|
DiffPyramid (CPN)
|
Learning Pyramid-structured Long-range Dependenci…
|
49.20
|
2025-06-03
|
|
|
GraphMLP
|
GraphMLP: A Graph MLP-Like Architecture for 3D Hu…
|
48.00
|
2022-06-13
|
|
|
Skeletal GNN
|
Learning Skeletal Graph Neural Networks for Hard …
|
47.90
|
2021-08-16
|
|
|
Virtual Bones (T=9 CPN)
|
Motion Projection Consistency Based 3D Human Pose…
|
47.40
|
2021-06-28
|
|
|
StridedTransformer (T=27)
|
Exploiting Temporal Contexts with Strided Transfo…
|
46.90
|
2021-03-26
|
|
|
VideoPose3D (T=243)
|
3D human pose estimation in video with temporal c…
|
46.80
|
2018-11-28
|
|
|
Trajectory Space Factorization (50 frames)
|
Trajectory Space Factorization for Deep Video-Bas…
|
46.60
|
2019-08-22
|
|
|
DC-GCT(T=1)
|
Double-chain Constraints for 3D Human Pose Estima…
|
46.10
|
2023-08-10
|
|
|
StridedTransformer (T=81)
|
Exploiting Temporal Contexts with Strided Transfo…
|
45.40
|
2021-03-26
|
|
|
HEMlets Pose
|
HEMlets Pose: Learning Part-Centric Heatmap Tripl…
|
45.10
|
2019-10-26
|
|
|
Pose Consensus (multi-view, est. calib.)
|
Consensus-based Optimization for 3D Human Pose Es…
|
45.00
|
2019-11-21
|
|
|
SRNet (T=243)
|
SRNet: Improving Generalization in 3D Human Pose …
|
44.80
|
2020-07-18
|
|
|
Attention (T=243 CPN)
|
Enhanced 3D Human Pose Estimation from Videos by …
|
44.80
|
2021-03-04
|
|
|
Virtual Bones (T=243 CPN)
|
Motion Projection Consistency Based 3D Human Pose…
|
44.80
|
2021-06-28
|
|
|
Shape-aware SMPL
|
Shape-Aware Human Pose and Shape Reconstruction U…
|
44.40
|
2019-08-26
|
|
|
PoseFormer (f=81)
|
3D Human Pose Estimation with Spatial and Tempora…
|
44.30
|
2021-03-18
|
|
|
RIE (T=243 CPN)
|
Improving Robustness and Accuracy via Relative In…
|
44.30
|
2021-07-29
|
|
|
Probabilistic Monocular (T=200)
|
Probabilistic Monocular 3D Human Pose Estimation …
|
44.30
|
2021-07-29
|
|
|
Anatomy3D
|
Anatomy-aware 3D Human Pose Estimation with Bone-…
|
44.10
|
2020-02-24
|
|
|
P-STMO-S (N=81)
|
P-STMO: Pre-Trained Spatial Temporal Many-to-One …
|
44.10
|
2022-03-15
|
|
|
StridedTransformer (T=243)
|
Exploiting Temporal Contexts with Strided Transfo…
|
44.00
|
2021-03-26
|
|
|
CrossFormer (T=81)
|
CrossFormer: Cross Spatio-Temporal Transformer fo…
|
43.70
|
2022-03-24
|
|
|
StridedTransformer (T=351)
|
Exploiting Temporal Contexts with Strided Transfo…
|
43.70
|
2021-03-26
|
|
|
ContextPose
|
Context Modeling in 3D Human Pose Estimation: A U…
|
43.40
|
2021-03-29
|
|
|
ConvFormer (T=243, CPN)
|
ConvFormer: Parameter Reduction in Transformer Mo…
|
43.20
|
2023-04-04
|
|
|
MHFormer
|
MHFormer: Multi-Hypothesis Transformer for 3D Hum…
|
43.00
|
2021-11-24
|
|
|
UGCN (HR-Net)
|
Motion Guided 3D Pose Estimation from Videos
|
42.60
|
2020-04-29
|
|
|
MixSTE (CPN, T=81)
|
MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for…
|
42.40
|
2022-03-02
|
|
|
P-STMO (N=243)
|
P-STMO: Pre-Trained Spatial Temporal Many-to-One …
|
42.10
|
2022-03-15
|
|
|
U-CondDGConv
|
Conditional Directed Graph Convolution for 3D Hum…
|
41.10
|
2021-07-16
|
|
|
GnTCN
|
Graph and Temporal Convolutional Networks for 3D …
|
40.90
|
2020-12-22
|
|
|
MixSTE (CPN, T=243)
|
MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for…
|
40.90
|
2022-03-02
|
|
|
IVT (f=5)
|
IVT: An End-to-End Instance-guided Video Transfor…
|
40.20
|
2022-08-06
|
|
|
Spatio-Temporal Network (T=128)
|
3D Human Pose Estimation using Spatio-Temporal Ne…
|
40.10
|
2020-04-07
|
|
|
MixSTE (HRNet, T=243)
|
MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for…
|
39.80
|
2022-03-02
|
|
|
Pose Consensus (multi-view, GT calib.)
|
Consensus-based Optimization for 3D Human Pose Es…
|
39.00
|
2019-11-21
|
|
|
SoloPose
|
SoloPose: One-Shot Kinematic 3D Human Pose Estima…
|
38.90
|
2023-12-15
|
|
|
PoseRN
|
PoseRN: A 2D pose refinement network for bias-fre…
|
38.40
|
2021-07-07
|
|
|
DiffPhy (W=480)
|
Differentiable Dynamics for Articulated 3d Human …
|
33.40
|
2022-05-24
|
|
|
KTPFormer (T=243)
|
KTPFormer: Kinematics and Trajectory Prior Knowle…
|
33.00
|
2024-03-31
|
|
|
Fusion-RPSM (t=10)
|
Cross View Fusion for 3D Human Pose Estimation
|
31.17
|
2019-09-03
|
|
|
FLEX
|
FLEX: Extrinsic Parameters-free Multi-view 3D Hum…
|
30.90
|
2021-05-05
|
|
|
LMT R50 224x224
|
Learnable human mesh triangulation for 3D human p…
|
30.56
|
2022-08-24
|
|
|
LWCDR
|
Lightweight Multi-View 3D Pose Estimation through…
|
30.20
|
2020-04-05
|
|
|
SmartEdgeSensor
|
Real-Time Multi-View 3D Human Pose Estimation usi…
|
29.80
|
2021-06-28
|
|
|
MTF-Transformer (M=0.4, T=1)
|
Adaptive Multi-view and Temporal Fusing Transform…
|
29.40
|
2021-10-11
|
|
|
Generalizable Human Pose Triangulation
|
Generalizable Human Pose Triangulation
|
29.10
|
2021-10-01
|
|
|
MTF-Transformer (M=0.4, T=7)
|
Adaptive Multi-view and Temporal Fusing Transform…
|
28.50
|
2021-10-11
|
|
|
Epipolar Transformer+R50 256×256+RPSM
|
Epipolar Transformers
|
26.90
|
2020-05-10
|
|
|
Geometry-Biased Transformer (HRNet)
|
Geometry-Biased Transformer for Robust Multi-View…
|
26.00
|
2023-12-28
|
|
|
LMT R152 384x384
|
Learnable human mesh triangulation for 3D human p…
|
17.59
|
2022-08-24
|
|