|
XFormer (HRNet)
|
XFormer: Fast and Accurate Monocular 3D Body Capt…
|
109.80
|
2023-05-18
|
|
|
DSR
|
Learning to Regress Bodies from Images using Diff…
|
104.70
|
2021-10-07
|
|
|
RSC-Net
|
3D Human Shape and Pose from a Single Low-Resolut…
|
103.36
|
2020-07-27
|
|
|
LMT R152 384x384
|
Learnable human mesh triangulation for 3D human p…
|
99.37
|
2022-08-24
|
|
|
TCPFormer (T=81)
|
TCPFormer: Learning Temporal Correlation with Imp…
|
99.00
|
2025-01-03
|
|
|
KTPFormer
|
KTPFormer: Kinematics and Trajectory Prior Knowle…
|
98.90
|
2024-03-31
|
|
|
RTPCA
|
Refined Temporal Pyramidal Compression-and-Amplif…
|
98.80
|
2023-09-04
|
|
|
TCPFormer (T=27)
|
TCPFormer: Learning Temporal Correlation with Imp…
|
98.70
|
2025-01-03
|
|
|
GLA-GCN (T=81)
|
GLA-GCN: Global-local Adaptive Graph Convolutiona…
|
98.53
|
2023-07-12
|
|
|
MotionAGFormer-S (T=81)
|
MotionAGFormer: Enhancing 3D Human Pose Estimatio…
|
98.30
|
2023-10-25
|
|
|
MotionAGFormer-B (T=81)
|
MotionAGFormer: Enhancing 3D Human Pose Estimatio…
|
98.30
|
2023-10-25
|
|
|
MotionAGFormer-L (T=81)
|
MotionAGFormer: Enhancing 3D Human Pose Estimatio…
|
98.20
|
2023-10-25
|
|
|
MotionAGFormer-XS (T=27)
|
MotionAGFormer: Enhancing 3D Human Pose Estimatio…
|
98.20
|
2023-10-25
|
|
|
HSTFormer (T=81)
|
HSTFormer: Hierarchical Spatial-Temporal Transfor…
|
98.00
|
2023-01-18
|
|
|
DiffPose
|
DiffPose: Toward More Reliable 3D Pose Estimation
|
98.00
|
2022-11-30
|
|
|
P-STMO (N=81)
|
P-STMO: Pre-Trained Spatial Temporal Many-to-One …
|
97.90
|
2022-03-15
|
|
|
PoseFormerV2 (T=81)
|
PoseFormerV2: Exploring Frequency Domain for Effi…
|
97.90
|
2023-03-30
|
|
|
Fusionformer (f=9)
|
(Fusionformer):Exploiting the Joint Motion Synerg…
|
97.90
|
2022-10-08
|
|
|
U-CondDGConv
|
Conditional Directed Graph Convolution for 3D Hum…
|
97.90
|
2021-07-16
|
|
|
DDT
|
DiffMesh: A Motion-aware Diffusion Framework for …
|
97.80
|
2023-03-23
|
|
|
D3DP (N=243, H=20, K=20, J-Agg)
|
Diffusion-Based 3D Human Pose Estimation with Mul…
|
97.70
|
2023-03-21
|
|
|
TCMR (T=16 w/o 3DPW)
|
Beyond Static Features for Temporally Consistent …
|
97.40
|
2020-11-17
|
|
|
MoCap-SPIN + PoseBERT
|
Leveraging MoCap Data for Human Mesh Recovery
|
97.40
|
2021-10-18
|
|
|
TCMR (T=16 w/o H3.6M)
|
Beyond Static Features for Temporally Consistent …
|
97.30
|
2020-11-17
|
|
|
MPS-Net (T=16)
|
Capturing Humans in Motion: Temporal-Attentive 3D…
|
96.70
|
2022-03-16
|
|
|
(R50-224) LMT
|
Learnable human mesh triangulation for 3D human p…
|
96.59
|
2022-08-24
|
|
|
ConvFormer
|
ConvFormer: Parameter Reduction in Transformer Mo…
|
96.40
|
2023-04-04
|
|
|
TePose (T=6 3DPW)
|
Live Stream Temporally Embedded 3D Human Body Pos…
|
96.20
|
2022-07-25
|
|
|
STR
|
Spatio-temporal Tendency Reasoning for Human Body…
|
95.30
|
2022-10-07
|
|
|
LMR
|
Learning Local Recurrent Models for Human Mesh Re…
|
94.60
|
2021-07-27
|
|
|
MixSTE (T=27)
|
MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for…
|
94.40
|
2022-03-02
|
|
|
MixSTE (T=1)
|
MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for…
|
94.20
|
2022-03-02
|
|
|
TAPE (T=16)
|
TAPE: Temporal Attention-based Probabilistic huma…
|
94.00
|
2023-04-29
|
|
|
GLoT
|
Global-to-Local Modeling for Video-based 3D Human…
|
93.90
|
2023-03-26
|
|
|
MHFormer
|
MHFormer: Multi-Hypothesis Transformer for 3D Hum…
|
93.80
|
2021-11-24
|
|
|
DST-VIBE
|
Deep Two-Stream Video Inference for Human Body Po…
|
93.40
|
2021-10-22
|
|
|
ZeDO (S=50)
|
Back to Optimization: Diffusion-based Zero-Shot 3…
|
93.00
|
2023-07-07
|
|
|
SPIN (Rigid Alignment)
|
Learning to Reconstruct 3D Human Pose and Shape v…
|
92.50
|
2019-09-27
|
|
|
PoseDA
|
Global Adaptation meets Local Generalization: Uns…
|
92.10
|
2023-03-29
|
|
|
Self-Attentive
|
Self-Attentive 3D Human Pose and Shape Estimation…
|
90.10
|
2021-03-26
|
|
|
VIBE
|
VIBE: Video Inference for Human Body Pose and Sha…
|
89.30
|
2019-12-11
|
|
|
PoseAug (+Extra2D)
|
PoseAug: A Differentiable Pose Augmentation Frame…
|
89.20
|
2021-05-06
|
|
|
CrossFormer
|
CrossFormer: Cross Spatio-Temporal Transformer fo…
|
89.10
|
2022-03-24
|
|
|
PoseTriplet
|
PoseTriplet: Co-evolving 3D Human Pose Estimation…
|
89.10
|
2022-03-29
|
|
|
VPose+PoseAug
|
PoseAug: A Differentiable Pose Augmentation Frame…
|
88.60
|
2021-05-06
|
|
|
PoseFormer (9 frames)
|
3D Human Pose Estimation with Spatial and Tempora…
|
88.60
|
2021-03-18
|
|
|
HybrIK-Transformer (HrNet-48)
|
3D Human Pose and Shape Estimation via HybrIK-Tra…
|
88.60
|
2023-02-09
|
|
|
Anatomy3D (T=81)
|
Anatomy-aware 3D Human Pose Estimation with Bone-…
|
87.90
|
2020-02-24
|
|
|
IKOL
|
IKOL: Inverse kinematics optimization layer for 3…
|
87.90
|
2023-02-02
|
|
|
Anatomy3D (T=243)
|
Anatomy-aware 3D Human Pose Estimation with Bone-…
|
87.80
|
2020-02-24
|
|
|
HybrIK
|
HybrIK: A Hybrid Analytical-Neural Inverse Kinema…
|
87.50
|
2020-11-30
|
|
|
DC-GCT
|
Double-chain Constraints for 3D Human Pose Estima…
|
87.50
|
2023-08-10
|
|
|
HybrIK (HRNet-W48)
|
HybrIK-X: Hybrid Analytical-Neural Inverse Kinema…
|
87.10
|
2023-04-12
|
|
|
UGCN
|
Motion Guided 3D Pose Estimation from Videos
|
86.90
|
2020-04-29
|
|
|
HTNet
|
HTNet: Human Topology Aware Network for 3D Human …
|
86.70
|
2023-02-20
|
|
|
PoseGU
|
PoseGU: 3D Human Pose Estimation with Novel Human…
|
86.30
|
2022-07-07
|
|
|
TAR (N=9)
|
Temporal-Aware Refinement for Video-based Human P…
|
85.90
|
2023-11-16
|
|
|
Regular Splitting Graph Network
|
Regular Splitting Graph Network for 3D Human Pose…
|
85.60
|
2023-05-09
|
|
|
MargiPose (multi-crop)
|
3D Human Pose Estimation with 2D Marginal Heatmaps
|
85.40
|
2018-06-05
|
|
|
HGN
|
Hierarchical Graph Networks for 3D Human Pose Est…
|
85.20
|
2021-11-23
|
|
|
Probabilistic Monocular
|
Probabilistic Monocular 3D Human Pose Estimation …
|
84.30
|
2021-07-29
|
|
|
Spatio-Temporal Network (T=128)
|
3D Human Pose Estimation using Spatio-Temporal Ne…
|
84.10
|
2020-04-07
|
|
|
PoseLifter
|
PoseLifter: Absolute 3D human pose lifting networ…
|
84.00
|
2019-10-26
|
|
|
Trajectory Space Factorization (F=25)
|
Trajectory Space Factorization for Deep Video-Bas…
|
83.60
|
2019-08-22
|
|
|
MAED
|
Encoder-decoder with Multi-level Attention for 3D…
|
83.60
|
2021-09-06
|
|
|
SSP-Net
|
SSP-Net: Scalable Sequential Pyramid Networks for…
|
83.20
|
2020-09-04
|
|
|
XNect (SelecSLS)
|
XNect: Real-time Multi-Person 3D Motion Capture w…
|
82.80
|
2019-07-01
|
|
|
RepNet (3DHP)
|
RepNet: Weakly Supervised Training of an Adversar…
|
82.50
|
2019-02-26
|
|
|
Skeletal GNN
|
Learning Skeletal Graph Neural Networks for Hard …
|
82.10
|
2021-08-16
|
|
|
RepNet (H36M)
|
RepNet: Weakly Supervised Training of an Adversar…
|
81.80
|
2019-02-26
|
|
|
EvoSkeleton
|
Cascaded deep monocular 3D human pose estimation …
|
81.20
|
2020-06-14
|
|
|
Multi-view Temporal self-supervised
|
Learning Temporal 3D Human Pose Estimation with P…
|
81.00
|
2021-10-14
|
|
|
Pose Consensus (monocular)
|
Consensus-based Optimization for 3D Human Pose Es…
|
80.60
|
2019-11-21
|
|
|
ContextPose
|
Context Modeling in 3D Human Pose Estimation: A U…
|
80.50
|
2021-03-29
|
|
|
GeoRep (fully-supervised)
|
Weakly-Supervised 3D Human Pose Learning via Mult…
|
80.20
|
2020-03-17
|
|
|
Graph Stacked Hourglass Network
|
Graph Stacked Hourglass Networks for 3D Human Pos…
|
80.10
|
2021-03-30
|
|
|
DynaBOA
|
Out-of-Domain Human Mesh Reconstruction via Dynam…
|
79.50
|
2021-11-07
|
|
|
VNect (ResNet 50 GT)
|
VNect: Real-time 3D Human Pose Estimation with a …
|
79.40
|
2017-05-03
|
|
|
WSGAN
|
Weakly Supervised Generative Network for Multiple…
|
79.30
|
2020-08-13
|
|
|
TIPSy-GAN (GT)
|
"Teaching Independent Parts Separately" (TIPSy-GA…
|
78.00
|
2022-05-12
|
|
|
SRNET
|
SRNet: Improving Generalization in 3D Human Pose …
|
77.60
|
2020-07-18
|
|
|
EpipolarPose (fully-supervised)
|
Self-Supervised Learning of 3D Human Pose using M…
|
77.50
|
2019-03-06
|
|
|
CanonPose
|
CanonPose: Self-Supervised Monocular 3D Human Pos…
|
77.00
|
2020-11-30
|
|
|
HR-Net+ST-GCN+PoseAug
|
PoseAug: A Differentiable Pose Augmentation Frame…
|
76.60
|
2021-05-06
|
|
|
VNect (Augm.)
|
VNect: Real-time 3D Human Pose Estimation with a …
|
76.60
|
2017-05-03
|
|
|
SPIN
|
Learning to Reconstruct 3D Human Pose and Shape v…
|
76.40
|
2019-09-27
|
|
|
PONet
|
PONet: Robust 3D Human Pose Estimation via Learni…
|
76.10
|
2021-12-21
|
|
|
Mehta
|
Monocular 3D Human Pose Estimation In The Wild Us…
|
75.70
|
2016-11-29
|
|
|
HEMlets Pose
|
HEMlets Pose: Learning Part-Centric Heatmap Tripl…
|
75.30
|
2019-10-26
|
|
|
Single-Shot Multi-Person
|
Single-Shot Multi-Person 3D Pose Estimation From …
|
75.20
|
2017-12-09
|
|
|
HR-Net+VPose+PoseAug
|
PoseAug: A Differentiable Pose Augmentation Frame…
|
73.20
|
2021-05-06
|
|
|
HMR
|
End-to-end Recovery of Human Shape and Pose
|
72.90
|
2017-12-18
|
|
|
Ordinal Depth Supervision
|
Ordinal Depth Supervision for 3D Human Pose Estim…
|
71.90
|
2018-05-10
|
|
|
ARTS (Resnet50 L=16)
|
ARTS: Semi-Analytical Regressor using Disentangle…
|
71.80
|
2024-10-21
|
|
|
Stereoscopic View Synthesis Subnetwork
|
Generalizing Monocular 3D Human Pose Estimation i…
|
71.20
|
2019-04-11
|
|
|
2D-3D Lifting Network
|
Unsupervised 3D Pose Estimation with Geometric Se…
|
71.10
|
2019-04-09
|
|
|
Adversarial Learning
|
3D Human Pose Estimation in the Wild by Adversari…
|
69.00
|
2018-03-26
|
|
|
MDM
|
Generating Multiple Hypotheses for 3D Human Pose …
|
67.90
|
2019-04-11
|
|
|
EFT
|
Exemplar Fine-Tuning for 3D Human Model Fitting T…
|
67.50
|
2020-04-07
|
|
|
Mehta
|
Monocular 3D Human Pose Estimation In The Wild Us…
|
64.70
|
2016-11-29
|
|
|
OriNet
|
OriNet: A Fully Convolutional Network for 3D Huma…
|
64.60
|
2018-11-12
|
|
|
PLIKS (HR48)
|
PLIKS: A Pseudo-Linear Inverse Kinematic Solver f…
|
54.10
|
2022-11-21
|
|
|
DG-Net (T=4)
|
Learning Dynamical Human-Joint Affinity for 3D Po…
|
53.80
|
2021-09-15
|
|
|
Ray3D (T=9 CPN H36M+HEva+3DHP)
|
Ray3D: ray-based 3D human pose estimation for mon…
|
46.60
|
2022-03-22
|
|
|
DC-GNet
|
DC-GNet: Deep Mesh Relation Capturing Graph Convo…
|
40.70
|
2021-08-27
|
|